Recent Releases of bentoml
bentoml - v1.4.22
What's Changed
- docs: Update diagram image by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5431
- chore(deps): bump actions/checkout from 4 to 5 by @dependabot[bot] in https://github.com/bentoml/BentoML/pull/5432
- fix: Correct argument merging logic in set_arguments function by @frostming in https://github.com/bentoml/BentoML/pull/5433
- feat: Add new GPU type 'amd-mi300x' to GpuLiteralType by @frostming in https://github.com/bentoml/BentoML/pull/5435
- feat: allow to get command later for service by @frostming in https://github.com/bentoml/BentoML/pull/5437
- fix: Add error handling for failed file downloads in JSONSerde and MultipartSerde by @frostming in https://github.com/bentoml/BentoML/pull/5436
- docs: Add examples by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5439
- fix: respect the metrics namespace passed from config by @frostming in https://github.com/bentoml/BentoML/pull/5440
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.21...v1.4.22
- Python
Published by frostming 9 months ago
bentoml - v1.4.20
What's Changed
- docs: Add rollback section by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5423
- feat: Replace usages of fs library with fsspec and pathlib by @frostming in https://github.com/bentoml/BentoML/pull/5424
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci[bot] in https://github.com/bentoml/BentoML/pull/5425
- fix: Add env var to disable local bentoml URL in requirements by @frostming in https://github.com/bentoml/BentoML/pull/5427
- chore(deps): bump actions/download-artifact from 4 to 5 by @dependabot[bot] in https://github.com/bentoml/BentoML/pull/5428
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.19...v1.4.20
- Python
Published by frostming 10 months ago
bentoml - v1.4.19
What's Changed
- fix: run post setup commands for codespace by @frostming in https://github.com/bentoml/BentoML/pull/5414
- fix: Ignore python.packages when requirements_txt is provided by @qimcis in https://github.com/bentoml/BentoML/pull/5421
- chore(deps): bump the pip group across 2 directories with 1 update by @dependabot[bot] in https://github.com/bentoml/BentoML/pull/5413
New Contributors
- @qimcis made their first contribution in https://github.com/bentoml/BentoML/pull/5421
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.18...v1.4.19
- Python
Published by frostming 10 months ago
bentoml - v1.4.18
What's Changed
- docs: Update contact us link by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5398
- docs: Update canary deployment by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5397
- docs: Add built-in status endpoints by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5400
- build: Use python3.10 package that exists on Ubuntu22.04 by @byronclark in https://github.com/bentoml/BentoML/pull/5403
- feat: better way to retrieve api token from CLI by @frostming in https://github.com/bentoml/BentoML/pull/5404
- docs: Add sandbox observability images by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5401
- fix: honor the default buckets in request duration metrics config by @frostming in https://github.com/bentoml/BentoML/pull/5405
- doc: sandboxes by @ssheng in https://github.com/bentoml/BentoML/pull/5411
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci[bot] in https://github.com/bentoml/BentoML/pull/5410
- docs: Move sandboxes doc to BentoCloud by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5412
- feat: add lastrequesttimestamp metric by @xianml in https://github.com/bentoml/BentoML/pull/5416
- docs: Update runtime doc for private pypi by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5415
- fix: missing secrets and canarys param in cli by @xianml in https://github.com/bentoml/BentoML/pull/5417
- fix: update assertions in IOMixin to enforce BaseModel subclassing by @frostming in https://github.com/bentoml/BentoML/pull/5419
- fix: description/readme too large by @xianml in https://github.com/bentoml/BentoML/pull/5420
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.17...v1.4.18
- Python
Published by frostming 10 months ago
bentoml - v1.4.17
What's Changed
- chore(config): export accelerator literal type by @aarnphm in https://github.com/bentoml/BentoML/pull/5384
- fix: accept bento type as the bento argument for deployment APIs by @frostming in https://github.com/bentoml/BentoML/pull/5385
- chore: return early python_packages by @aarnphm in https://github.com/bentoml/BentoML/pull/5387
- docs: Update adaptive batching example by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5388
- feat: reading bento args from a YAML file by @frostming in https://github.com/bentoml/BentoML/pull/5389
- docs: Add --arg-file flag by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5391
- fix: Adjust keras version comparison by @rmarquis in https://github.com/bentoml/BentoML/pull/5392
- chore: update AWS cloudformation template by @sauyon in https://github.com/bentoml/BentoML/pull/5394
- docs: Add canary deployment by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5390
- docs: Add BentoML Sandboxes by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5396
- feat: support canary for bentoml deployment apply commands by @xianml in https://github.com/bentoml/BentoML/pull/5395
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.16...v1.4.17
- Python
Published by frostming 11 months ago
bentoml - v1.4.16
What's Changed
- docs: Add codespaces video by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5370
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/5378
- feat: read dependencies from uv lock by @frostming in https://github.com/bentoml/BentoML/pull/5379
- refactor: move legacy APIs to a separate module by @frostming in https://github.com/bentoml/BentoML/pull/5381
- feat: support custom service start command by @frostming in https://github.com/bentoml/BentoML/pull/5382
- fix: better way to set service name by @frostming in https://github.com/bentoml/BentoML/pull/5383
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.15...v1.4.16
- Python
Published by frostming 12 months ago
bentoml - v1.4.15
What's Changed
- docs: Add CI/CD pipeline doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5366
- fix: disable GPU allocation if CUDAVISIBLEDEVICES is set by @frostming in https://github.com/bentoml/BentoML/pull/5368
- fix: race condition issue initializing result db by @frostming in https://github.com/bentoml/BentoML/pull/5369
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.14...v1.4.15
- Python
Published by frostming about 1 year ago
bentoml - v1.4.14
What's Changed
- chore: fix link in readme by @imba-tjd in https://github.com/bentoml/BentoML/pull/5353
- docs: correct description of maxlatencyms by @jianshen92 in https://github.com/bentoml/BentoML/pull/5348
- feat: support --arg for bentoml deployment create and update by @frostming in https://github.com/bentoml/BentoML/pull/5354
- docs: reword some docs and a handful of typos by @b8zhong in https://github.com/bentoml/BentoML/pull/5356
- fix: align the task status with bentocloud by @frostming in https://github.com/bentoml/BentoML/pull/5359
- fix: compatible implementation for evaltypelenient by @frostming in https://github.com/bentoml/BentoML/pull/5358
- docs: Add triton example by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5357
- docs: stabilization window by @jianshen92 in https://github.com/bentoml/BentoML/pull/5360
- docs: replace outdated deployment parameter by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5361
- fix: apply stabilization window config by @jianshen92 in https://github.com/bentoml/BentoML/pull/5362
- fix: allow route name without leading slash by @jianshen92 in https://github.com/bentoml/BentoML/pull/5363
- fix(deployment): remove duplicated
--config-fileby @b8zhong in https://github.com/bentoml/BentoML/pull/5364
New Contributors
- @imba-tjd made their first contribution in https://github.com/bentoml/BentoML/pull/5353
- @b8zhong made their first contribution in https://github.com/bentoml/BentoML/pull/5356
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.13...v1.4.14
- Python
Published by frostming about 1 year ago
bentoml - v1.4.13
What's Changed
- docs: Fix BentoCloud CLI link by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5340
- chore(deps): bump astral-sh/setup-uv from 5 to 6 by @dependabot in https://github.com/bentoml/BentoML/pull/5341
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/5342
- fix: subclass checking for client classes by @frostming in https://github.com/bentoml/BentoML/pull/5345
- fix: insert install command even if the base image is specified by @frostming in https://github.com/bentoml/BentoML/pull/5344
- fix: do not allow separate python requirements calls by @frostming in https://github.com/bentoml/BentoML/pull/5347
- fix: support pre-built wheels in bento spec v2 by @frostming in https://github.com/bentoml/BentoML/pull/5349
- feat: add paths to schemas to support openai chat endpoints by @aarnphm in https://github.com/bentoml/BentoML/pull/5346
- fix: delete preheatpippackages by @bojiang in https://github.com/bentoml/BentoML/pull/5350
- docs: Add docs for wheels and run_script() by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5351
- chore: minor fix, wrong message by @frostming in https://github.com/bentoml/BentoML/pull/5352
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.12...v1.4.13
- Python
Published by frostming about 1 year ago
bentoml - v1.4.12
What's Changed
- docs: Use command to list GPU types by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5330
- chore: disable progress bar on cloud build by @aarnphm in https://github.com/bentoml/BentoML/pull/5331
- fix: handling equal sign in value of secret by @larme in https://github.com/bentoml/BentoML/pull/5332
- fix: make sure to inherit from base image ENV by @aarnphm in https://github.com/bentoml/BentoML/pull/5334
- fix: don't add duplicate global options to requirements.txt by @frostming in https://github.com/bentoml/BentoML/pull/5336
- fix: don't restore cwd when importing service in worker by @frostming in https://github.com/bentoml/BentoML/pull/5339
- docs: Unify image styles with BentoML theme by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5338
- feat: custom readiness hook method by @frostming in https://github.com/bentoml/BentoML/pull/5337
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.10...v1.4.12
- Python
Published by aarnphm about 1 year ago
bentoml - v1.4.10
What's Changed
- doc: Update saml.rst by @bojiang in https://github.com/bentoml/BentoML/pull/5309
- docs: Add template arg doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5311
- chore: update gpu_type for supported GPU on bentocloud by @aarnphm in https://github.com/bentoml/BentoML/pull/5312
- doc: rename PythonImage to Image by @frostming in https://github.com/bentoml/BentoML/pull/5313
- docs: add monitoring API tokens section to manage-api-tokens.rst by @Haivilo in https://github.com/bentoml/BentoML/pull/5316
- feat: show fastapi routes in playground ui by @frostming in https://github.com/bentoml/BentoML/pull/5314
- fix: add /app/.venv/bin to PATH to support Kubernetes exec-style entrypoints by @restato in https://github.com/bentoml/BentoML/pull/5315
- fix: Merge command line args with the ones in the config file by @frostming in https://github.com/bentoml/BentoML/pull/5317
- doc: add examples of bentoml deploy for bento args by @frostming in https://github.com/bentoml/BentoML/pull/5318
- fix: usage tracking for bentoml build by @frostming in https://github.com/bentoml/BentoML/pull/5321
- revert: "feat: show fastapi routes in playground ui" by @frostming in https://github.com/bentoml/BentoML/pull/5323
- fix: only regard the positional arg as build ctx if it is a local dir by @frostming in https://github.com/bentoml/BentoML/pull/5322
- fix: make sure to use self.args in with_defaults by @aarnphm in https://github.com/bentoml/BentoML/pull/5324
New Contributors
- @restato made their first contribution in https://github.com/bentoml/BentoML/pull/5315
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.8...v1.4.10
- Python
Published by frostming about 1 year ago
bentoml - v1.4.8
What's Changed
- feat: make it possible to override values of Image from bentofile.yaml by @frostming in https://github.com/bentoml/BentoML/pull/5298
- feat: implement bento arguments by @frostming in https://github.com/bentoml/BentoML/pull/5299
- fix: add end of line if the requirments file doesn't have by @frostming in https://github.com/bentoml/BentoML/pull/5302
- docs(security): update security advisory email by @ssheng in https://github.com/bentoml/BentoML/pull/5304
- fix: remove start commands from CLI by @frostming in https://github.com/bentoml/BentoML/pull/5303
- chore: update security notes by @frostming in https://github.com/bentoml/BentoML/pull/5305
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/5306
- chore: locking transformers <4.51 for quickstart tests by @aarnphm in https://github.com/bentoml/BentoML/pull/5307
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.7...v1.4.8
- Python
Published by frostming about 1 year ago
bentoml - v1.4.7
What's Changed
- docs(saml): add sso saml doc by @ssheng in https://github.com/bentoml/BentoML/pull/5292
- docs: Add some diagrams for get started section by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5285
- fix: do not start dependency if it's from a URL or deployment by @frostming in https://github.com/bentoml/BentoML/pull/5293
- feat: support packgitpackages and fix add group for alpine by @frostming in https://github.com/bentoml/BentoML/pull/5295
- fix: initialize async http client with async method by @frostming in https://github.com/bentoml/BentoML/pull/5296
- feat: support --name option for bentoml build and bentoml code by @frostming in https://github.com/bentoml/BentoML/pull/5297
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.6...v1.4.7
- Python
Published by aarnphm about 1 year ago
bentoml - v1.4.6
What's Changed
- docs: Add org token doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5277
- docs: remove openllm from examples overview by @ssheng in https://github.com/bentoml/BentoML/pull/5278
- fix: format substitution by @byronclark in https://github.com/bentoml/BentoML/pull/5279
- fix: add missing .route of __endpoint by @reobroqn in https://github.com/bentoml/BentoML/pull/5281
- fix: non-standard ssh git url by @frostming in https://github.com/bentoml/BentoML/pull/5282
- docs: Update adaptive batching doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5283
- docs: Add BentoOCR to example list by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5284
- docs: Update private repo notes by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5262
- fix: replace namespace import to
python_multipartby @yxtay in https://github.com/bentoml/BentoML/pull/5280 - docs: Fix format by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5287
- chore: better visibility by @bojiang in https://github.com/bentoml/BentoML/pull/5288
- fix: on load bento for dependent services by @frostming in https://github.com/bentoml/BentoML/pull/5286
- fix: visibility by @bojiang in https://github.com/bentoml/BentoML/pull/5289
- fix: wrong error context by @frostming in https://github.com/bentoml/BentoML/pull/5291
New Contributors
- @byronclark made their first contribution in https://github.com/bentoml/BentoML/pull/5279
- @reobroqn made their first contribution in https://github.com/bentoml/BentoML/pull/5281
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.5...v1.4.6
- Python
Published by frostming about 1 year ago
bentoml - v1.4.4
What's Changed
- feat: update readme by @ssheng in https://github.com/bentoml/BentoML/pull/5259
- docs: Add update command to cloud deployment doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5260
- fix: fallback to v1 if pack git packages is set by @frostming in https://github.com/bentoml/BentoML/pull/5261
- build: Smaller docker images by @jeffmarshall in https://github.com/bentoml/BentoML/pull/5264
- feat(serve): add
--envand inject service-defined envs to serving environment by @aarnphm in https://github.com/bentoml/BentoML/pull/5263 - docs(tasks): update async tasks docs by @ssheng in https://github.com/bentoml/BentoML/pull/5266
- feat(client): add task apis to client methods by @frostming in https://github.com/bentoml/BentoML/pull/5265
- feat: default min replicas is None by @yetone in https://github.com/bentoml/BentoML/pull/5268
- tests: banning pickle requests by @frostming in https://github.com/bentoml/BentoML/pull/5269
- feat: Fail fast when running inside container by @frostming in https://github.com/bentoml/BentoML/pull/5270
- docs(byoc): update aws byoc role template link by @ssheng in https://github.com/bentoml/BentoML/pull/5272
- docs: Update langgraph example by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5273
- fix(supervisor): quit the arbiter correctly by @frostming in https://github.com/bentoml/BentoML/pull/5274
- fix: preserve global options in requirements.txt by @frostming in https://github.com/bentoml/BentoML/pull/5275
New Contributors
- @jeffmarshall made their first contribution in https://github.com/bentoml/BentoML/pull/5264
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.3...v1.4.4
- Python
Published by frostming about 1 year ago
bentoml - v1.4.3
What's Changed
- docs: Update examples to use new APIs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5252
- Add alt text to all images in documentation by @devin-ai-integration in https://github.com/bentoml/BentoML/pull/5253
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/5254
- docs: update deprecated links by @aarnphm in https://github.com/bentoml/BentoML/pull/5256
- docs: Add root input usage by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5257
- fix: reformat the code by @frostming in https://github.com/bentoml/BentoML/pull/5258
- fix: forbid requests with pickle encoding at the entry service
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.2...v1.4.3
- Python
Published by frostming about 1 year ago
bentoml - v1.4.2
What's Changed
- Fix RunPod unhashable model error by converting svc.models to hashable ids by @rivaon in https://github.com/bentoml/BentoML/pull/5244
- fix(io): OpenAPI schema for multipart form request body by @frostming in https://github.com/bentoml/BentoML/pull/5249
- fix: drop uv as a hard dependency by @frostming in https://github.com/bentoml/BentoML/pull/5238
- docs: Update examples to use new HF API by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5242
- refactor: drop deepmerge dependency by @frostming in https://github.com/bentoml/BentoML/pull/5250
- refactor: unify logic of loading service by @frostming in https://github.com/bentoml/BentoML/pull/5232
- fix: collect requirements from image spec for codespaces by @frostming in https://github.com/bentoml/BentoML/pull/5251
New Contributors
- @rivaon made their first contribution in https://github.com/bentoml/BentoML/pull/5244
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.1...v1.4.2
- Python
Published by frostming over 1 year ago
bentoml - v1.4.1
What's Changed
- docs: use diff for runtime image by @parano in https://github.com/bentoml/BentoML/pull/5236
- docs: Update runtime explanations by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5240
- fix(regression): call error when context parameter is present by @frostming in https://github.com/bentoml/BentoML/pull/5247
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.4.0...v1.4.1
- Python
Published by frostming over 1 year ago
bentoml - v1.4.0
We are thrilled to announce the release of BentoML 1.4! This version introduces several new features and improvements to accelerate your iteration cycle and enhance the overall developer experience.
Below are the key highlights of 1.4, and you can find more details in the release blog post.
🚀 20x faster iteration with Codespaces
- Introduced BentoML Codespaces, a development platform built on BentoCloud
- Added the
bentoml codecommand for creating a Codespace - Auto-sync of local changes to the cloud environment
- Access to a variety of powerful cloud GPUs
- Real-time logs and debugging through the cloud dashboard
- Eliminate dependency headaches and ensure consistency between dev and prod environments
🐍 New Python SDK for runtime configurations
- Added
bentoml.images.PythonImagefor defining the Bento runtime environment in Python instead of usingbentofile.yamlorpyproject.toml - Support customizing runtime configurations (e.g., Python version, system packages, and dependencies) directly in the
service.pyfile - Introduced context-sensitive
run()method for running custom build commands - Backward compatible with existing
bentofile.yamlandpyproject.tomlconfigurations
⚡ Accelerated model loading with safetensors
- Implemented build-time model downloads and parallel loading of model weights using safetensors to reduce cold start time and improve scaling performance. See the documentation to learn more.
- Added
bentoml.models.HuggingFaceModelfor loading models from HF. It supports private model repositories and custom endpoints - Added
bentoml.models.BentoModelfor loading models from BentoCloud and the Model Store
🌍 External deployment dependencies
- Extended
bentoml.depends()to support external deployments - Added support for calling BentoCloud Deployments via name or URL
- Added support for calling self-hosted HTTP AI services outside BentoCloud
⚠️ Legacy Service API deprecation
- The legacy
bentoml.ServiceAPI (with runners) is now officially deprecated and is scheduled for removal in a future release. We recommend you use the@bentoml.servicedecorator.
Note that:
1.4remains fully compatible with Bentos created by1.3.- The BentoML documentation has been updated with examples and guides for
1.4.
🙏 As always, we appreciate your continued support!
What's Changed
- feat: support bentoml serve without service name by @frostming in https://github.com/bentoml/BentoML/pull/5208
- feat(service): expose service-level labels definition by @aarnphm in https://github.com/bentoml/BentoML/pull/5211
- fix: restore path after import by @frostming in https://github.com/bentoml/BentoML/pull/5214
- fix: compile bytecode when installing python packages by @frostming in https://github.com/bentoml/BentoML/pull/5212
- fix: IO descriptor honor validators by @frostming in https://github.com/bentoml/BentoML/pull/5213
- feat(image): add support for chaining
.pyproject.tomlby @aarnphm in https://github.com/bentoml/BentoML/pull/5218 - feat: support root input spec using positonal-only argument by @frostming in https://github.com/bentoml/BentoML/pull/5217
- fix: gradio error when uploading file by @frostming in https://github.com/bentoml/BentoML/pull/5220
- fix: input data validation for root input by @frostming in https://github.com/bentoml/BentoML/pull/5221
- fix: don't restore model store after importing service by @frostming in https://github.com/bentoml/BentoML/pull/5223
- feat(metrics): extend histogram buckets to support LLM latencies by @devin-ai-integration in https://github.com/bentoml/BentoML/pull/5222
- fix: always add bentoml req unless it is specified as a url dependency by @frostming in https://github.com/bentoml/BentoML/pull/5225
- docs: update links to examples by @aarnphm in https://github.com/bentoml/BentoML/pull/5224
- docs: add environment variable authentication documentation by @devin-ai-integration in https://github.com/bentoml/BentoML/pull/5231
- docs: Update docs to use new runtime API by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5177
- fix: add files under env/docker by @frostming in https://github.com/bentoml/BentoML/pull/5234
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.22...v1.4.0
- Python
Published by frostming over 1 year ago
bentoml - v1.4.0a1
What's Changed
- feat: support bentoml serve without service name by @frostming in https://github.com/bentoml/BentoML/pull/5208
- feat(service): expose service-level labels definition by @aarnphm in https://github.com/bentoml/BentoML/pull/5211
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.22...v1.4.0a1
- Python
Published by frostming over 1 year ago
bentoml - v1.3.22
What's Changed
- fix: add line endings for python_packages(...) by @frostming in https://github.com/bentoml/BentoML/pull/5203
- fix: correct the log for locking platform by @frostming in https://github.com/bentoml/BentoML/pull/5205
- fix: uv installation in container by @frostming in https://github.com/bentoml/BentoML/pull/5206
- fix: add cluster option for secrets command by @xianml in https://github.com/bentoml/BentoML/pull/5209
- fix(build): setattr frozen sets by @aarnphm in https://github.com/bentoml/BentoML/pull/5207
- fix:correct context path when serving from bento by @frostming in https://github.com/bentoml/BentoML/pull/5210
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.21...v1.3.22
- Python
Published by frostming over 1 year ago
bentoml - v1.3.21
What's Changed
- docs: correct types for example by @NitzanShwartz in https://github.com/bentoml/BentoML/pull/5188
- fix: make all top-level attributes lazy by @frostming in https://github.com/bentoml/BentoML/pull/5184
- fix: mounted apps don't eagerly match path prefix by @frostming in https://github.com/bentoml/BentoML/pull/5190
- chore: add spec into bento manifest schema by @xianml in https://github.com/bentoml/BentoML/pull/5192
- fix: get commit id from requested revision when it is missing by @frostming in https://github.com/bentoml/BentoML/pull/5193
- feat: add @bentoml.on_startup decorator by @devin-ai-integration in https://github.com/bentoml/BentoML/pull/5194
- fix: conditionally include endpoint_urls in deployment dictionary by @Haivilo in https://github.com/bentoml/BentoML/pull/5195
- fix: enable image spec by default by @frostming in https://github.com/bentoml/BentoML/pull/5197
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/5200
- docs: update AWS byoc cloudformation template by @sauyon in https://github.com/bentoml/BentoML/pull/5201
- feat: support running scripts in new image spec by @frostming in https://github.com/bentoml/BentoML/pull/5196
New Contributors
- @NitzanShwartz made their first contribution in https://github.com/bentoml/BentoML/pull/5188
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.20...v1.3.21
- Python
Published by frostming over 1 year ago
bentoml - v1.3.20
What's Changed
- Add logging for service cleanup hooks in new-style BentoML services by @devin-ai-integration in https://github.com/bentoml/BentoML/pull/5171
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/5170
- fix: set the arbiter thread to be daemon thread by @frostming in https://github.com/bentoml/BentoML/pull/5172
- chore(analytics): use utils
is_jupyterto determine notebook state by @aarnphm in https://github.com/bentoml/BentoML/pull/5173 - docs: Add comfyUI example doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5148
- fix: allow building bento without build config file by @frostming in https://github.com/bentoml/BentoML/pull/5175
- fix: Remove distutils dependency by @jaume-ferrarons in https://github.com/bentoml/BentoML/pull/5179
- docs: Add streaming and websocket docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5180
- docs: Update ASGI decorator by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5182
- fix: allow usage like bentoml deploy service:MyService by @frostming in https://github.com/bentoml/BentoML/pull/5181
- docs: Update Gradio example link by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5183
- fix: use a specific manylinux version as build platform for better compatibility by @frostming in https://github.com/bentoml/BentoML/pull/5185
- feat(metrics): init zero for request count of apis by @Haivilo in https://github.com/bentoml/BentoML/pull/5186
New Contributors
- @devin-ai-integration made their first contribution in https://github.com/bentoml/BentoML/pull/5171
- @jaume-ferrarons made their first contribution in https://github.com/bentoml/BentoML/pull/5179
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.19...v1.3.20
- Python
Published by frostming over 1 year ago
bentoml - v1.3.19
What's Changed
- fix: turn off build log stream in jupyter notebook by @frostming in https://github.com/bentoml/BentoML/pull/5165
- docs: Add notes for loading HF private models by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5166
- fix: patch annotations inside a container type by @frostming in https://github.com/bentoml/BentoML/pull/5167
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.18...v1.3.19
- Python
Published by frostming over 1 year ago
bentoml - v1.3.18
What's Changed
- docs: Simplify model composition doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5147
- docs: Restructure image folder and add alt for SEO by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5150
- docs: Fix links by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5153
- docs: Merge examples to io type doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5152
- fix: Permission issue of uv python installation directory by @frostming in https://github.com/bentoml/BentoML/pull/5151
- fix: lazy safetensor patch by @frostming in https://github.com/bentoml/BentoML/pull/5149
- docs: Clean up examples folder by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5154
- fix: use kantoku instead of circus by @bojiang in https://github.com/bentoml/BentoML/pull/5155
- fix: Update lock file by @frostming in https://github.com/bentoml/BentoML/pull/5156
- fix: use emoji code instead of emoji char by @frostming in https://github.com/bentoml/BentoML/pull/5157
- fix: set model revision correctly by @frostming in https://github.com/bentoml/BentoML/pull/5158
- fix: add missing secrets params in bentoml sdk by @xianml in https://github.com/bentoml/BentoML/pull/5159
- fix: expose cloud api to get a single model by @frostming in https://github.com/bentoml/BentoML/pull/5160
- fix: use the same spinner for bento and model apis by @frostming in https://github.com/bentoml/BentoML/pull/5161
- fix: closed file descriptior issue by @frostming in https://github.com/bentoml/BentoML/pull/5162
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.17...v1.3.18
- Python
Published by frostming over 1 year ago
bentoml - v1.3.17
What's Changed
- docs: Simplify packaging docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5116
- docs: Fix links by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5124
- docs: Update API tokens doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5125
- fix: image builder log stream doesn't work by @frostming in https://github.com/bentoml/BentoML/pull/5126
- docs: Add GPU access messaging by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5127
- fix: disable markup and highlight for image log stream by @frostming in https://github.com/bentoml/BentoML/pull/5129
- fix: don't override built-in function by @frostming in https://github.com/bentoml/BentoML/pull/5131
- fix: add default install command for image spec by @frostming in https://github.com/bentoml/BentoML/pull/5130
- docs: Update examples by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5128
- fix: loosen the constraints of opentelemetry dependencies by @frostming in https://github.com/bentoml/BentoML/pull/5134
- fix: only honor ctx or context parameter with correct annotation by @frostming in https://github.com/bentoml/BentoML/pull/5135
- fix: temp file is deleted unexpected on Windows by @frostming in https://github.com/bentoml/BentoML/pull/5133
- docs: Update old comfyui doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5137
- feat: install packages into venv and chown by @frostming in https://github.com/bentoml/BentoML/pull/5136
- docs: Update onboarding docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5138
- fix: raise error when certfile is not given but ssl enabled and fix local dep by @frostming in https://github.com/bentoml/BentoML/pull/5139
- fix: bad file descirptor issue when deploying bento by @frostming in https://github.com/bentoml/BentoML/pull/5142
- feat: select a subset of files for huggingface models by @frostming in https://github.com/bentoml/BentoML/pull/5144
- docs: Update example overview by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5143
- docs: Fix images by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5145
- fix: use content hash as the default model version by @frostming in https://github.com/bentoml/BentoML/pull/5146
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.16...v1.3.17
- Python
Published by frostming over 1 year ago
bentoml - v1.3.16
What's Changed
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/5108
- docs: Simplify Adaptive batching docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5107
- docs: Update homepage messaging by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5105
- fix: add basic metrics and access logs for websocket by @frostming in https://github.com/bentoml/BentoML/pull/5109
- fix: ensure all models to exists on deployment by @frostming in https://github.com/bentoml/BentoML/pull/5110
- fix: enable image spec when image is explictly given by @frostming in https://github.com/bentoml/BentoML/pull/5114
- fix: drop the redundant parameter for runner_service by @frostming in https://github.com/bentoml/BentoML/pull/5115
- docs: Fix links by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5111
- feat: support post commands in image spec by @frostming in https://github.com/bentoml/BentoML/pull/5118
- feat: add
--with-modelsoption tobentoml pullcommand by @frostming in https://github.com/bentoml/BentoML/pull/5117 - docs: Update cloud deployment doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5119
- docs: Fix typo by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5121
- docs: Fix links by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5122
- fix: calculate bentofile path against cwd if given explicitly by @frostming in https://github.com/bentoml/BentoML/pull/5123
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.15...v1.3.16
- Python
Published by frostming over 1 year ago
bentoml - v1.3.15
What's Changed
- docs: doc refactoring by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5089
- docs: Fix invalid icon images by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5096
- docs: Update readme examples and add distributed service doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5097
- fix: protect model repository creation with a lock to avoid a race condition by @frostming in https://github.com/bentoml/BentoML/pull/5095
- fix: generate schema compatible with pydantic>=2.10 by @frostming in https://github.com/bentoml/BentoML/pull/5100
- docs: Modify 'metric' menu link on 'observability index' page by @jin-daram in https://github.com/bentoml/BentoML/pull/5101
- fix: fix bug of serialization error and runner can't be shutdown by @frostming in https://github.com/bentoml/BentoML/pull/5103
- feat(cli): Support passing key value pairs from reading a dotenv file by @frostming in https://github.com/bentoml/BentoML/pull/5104
- fix: calculate readme file path from build ctx rather than cwd by @frostming in https://github.com/bentoml/BentoML/pull/5106
New Contributors
- @jin-daram made their first contribution in https://github.com/bentoml/BentoML/pull/5101
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.14...v1.3.15
- Python
Published by frostming over 1 year ago
bentoml - v1.3.14
What's Changed
- docs: update
buf.yamlreference by @emmanuel-ferdman in https://github.com/bentoml/BentoML/pull/5090 - fix: read stream before accessing response.text by @frostming in https://github.com/bentoml/BentoML/pull/5091
- fix: set manifest.dev for bare bento upload by @frostming in https://github.com/bentoml/BentoML/pull/5092
- fix: pin pydantic to < 2.10 and restore cwd when building bento by @frostming in https://github.com/bentoml/BentoML/pull/5093
New Contributors
- @emmanuel-ferdman made their first contribution in https://github.com/bentoml/BentoML/pull/5090
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.13...v1.3.14
- Python
Published by bojiang over 1 year ago
bentoml - v1.3.13
What's Changed
- fix: build git repo with uv by @frostming in https://github.com/bentoml/BentoML/pull/5085
- fix: use the model_id in bento by @frostming in https://github.com/bentoml/BentoML/pull/5087
- fix: create dir before move by @frostming in https://github.com/bentoml/BentoML/pull/5088
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.12...v1.3.13
- Python
Published by frostming over 1 year ago
bentoml - v1.3.12
What's Changed
- fix: correct file response for internal service calling by @frostming in https://github.com/bentoml/BentoML/pull/5071
- docs: Add explanations for model loading acceleration by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5066
- docs: Refactor examples by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5065
- docs: Update codespaces desc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5072
- fix: don't ignore empty dirs when unpacking model and bento by @frostming in https://github.com/bentoml/BentoML/pull/5073
- docs: Remove dead link by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5075
- docs: Add doc canonical link by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5076
- doc: add comfyui example by @ssheng in https://github.com/bentoml/BentoML/pull/5077
- doc: update comfyui to include export instructions by @ssheng in https://github.com/bentoml/BentoML/pull/5078
- doc: update diffusion models to include comfyui by @ssheng in https://github.com/bentoml/BentoML/pull/5079
- docs: Update examples index by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5080
- fix: move monitoring project to tests folder by @frostming in https://github.com/bentoml/BentoML/pull/5081
- docs: Update example list by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5083
- fix: check dependency close method (#5082) by @yxtay in https://github.com/bentoml/BentoML/pull/5084
- fix: empty doc for bare built bento by @xianml in https://github.com/bentoml/BentoML/pull/5086
New Contributors
- @yxtay made their first contribution in https://github.com/bentoml/BentoML/pull/5084
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.11...v1.3.12
- Python
Published by frostming over 1 year ago
bentoml - v1.3.11
What's Changed
- fix: spark usage following API change by @frostming in https://github.com/bentoml/BentoML/pull/5052
- docs: Add model loading doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5049
- doc: suggest to use pip for CUDA first by @bojiang in https://github.com/bentoml/BentoML/pull/5054
- docs: Update build-options.rst by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5055
- fix: use the model revision in bento info for huggingface models by @frostming in https://github.com/bentoml/BentoML/pull/5053
- feat: Adding SDK support for deployment labels by @jianshen92 in https://github.com/bentoml/BentoML/pull/5057
- fix: postpone the model id normalization for huggingface models by @frostming in https://github.com/bentoml/BentoML/pull/5060
- chore: upload descripiton to remote bento store by @xianml in https://github.com/bentoml/BentoML/pull/5047
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/5061
- feat: Add task_id to request inference context by @Leon-Sander in https://github.com/bentoml/BentoML/pull/5059
- chore: copy existing README.md instead of creating a new one by @xianml in https://github.com/bentoml/BentoML/pull/5063
- feat: allow extending bentoml with extra commands by @frostming in https://github.com/bentoml/BentoML/pull/5064
- fix: remove the version limit of pynvml by @frostming in https://github.com/bentoml/BentoML/pull/5068
New Contributors
- @Leon-Sander made their first contribution in https://github.com/bentoml/BentoML/pull/5059
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.10...v1.3.11
- Python
Published by frostming over 1 year ago
bentoml - v1.3.10
What's Changed
- fix: [bug bash] prefetch url by @xianml in https://github.com/bentoml/BentoML/pull/5028
- fix: trigger reset when system package changes; find dependent by @frostming in https://github.com/bentoml/BentoML/pull/5027
- fix(decorator): reject wrapper as dunder methods by @aarnphm in https://github.com/bentoml/BentoML/pull/5030
- fix: upload a flag file after project ready by @frostming in https://github.com/bentoml/BentoML/pull/5029
- fix: update spinner with the service readyz status by @frostming in https://github.com/bentoml/BentoML/pull/5031
- docs: Add IO tables by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5032
- docs: Create secrets for deployment by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5034
- doc: api docs for build and build_bentofile by @frostming in https://github.com/bentoml/BentoML/pull/5035
- feat: validate required envs when creating deployment by @frostming in https://github.com/bentoml/BentoML/pull/5033
- docs: fix links by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5036
- docs: Add Gradio integration by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5040
- fix: remove duplicate logs by @frostming in https://github.com/bentoml/BentoML/pull/5038
- docs: Add byoc request quota by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5037
- feat: Opt-in bento image support by @frostming in https://github.com/bentoml/BentoML/pull/5039
- feat: support reading build config and dependencies from pyproject.toml by @frostming in https://github.com/bentoml/BentoML/pull/5042
- docs: Add doc for external deployment dependency by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5043
- docs: Add Base Hyperlint Config by @bllchmbrs in https://github.com/bentoml/BentoML/pull/5041
- fix: reconstruct build config for getting requirement by @frostming in https://github.com/bentoml/BentoML/pull/5045
- docs: Add LangGraph example doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5046
- docs: Add codespaces doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5044
New Contributors
- @bllchmbrs made their first contribution in https://github.com/bentoml/BentoML/pull/5041
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.9...v1.3.10
- Python
Published by frostming over 1 year ago
bentoml - v1.3.9
What's Changed
- fix: add a flag to mark dev bento by @frostming in https://github.com/bentoml/BentoML/pull/5021
- docs: Fix typo by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5022
- fix: circus graceful shutdown by @bojiang in https://github.com/bentoml/BentoML/pull/5024
- fix: emit deprecation warings for legacy APIs by @frostming in https://github.com/bentoml/BentoML/pull/5023
- fix: skip safetensor patching if not installed by @frostming in https://github.com/bentoml/BentoML/pull/5025
- doc: update aws byoc by @ssheng in https://github.com/bentoml/BentoML/pull/5026
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.8...v1.3.9
- Python
Published by frostming over 1 year ago
bentoml - v1.3.8
What's Changed
- doc: Update shieldgemma doc name by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4999
- fix: tolerate build error when watching for changes by @frostming in https://github.com/bentoml/BentoML/pull/5000
- doc: correct the requirements by @frostming in https://github.com/bentoml/BentoML/pull/5001
- fix: expose errors occurring before the first yield of stream response by @frostming in https://github.com/bentoml/BentoML/pull/5002
- doc: fix endpoint url related typos by @ssheng in https://github.com/bentoml/BentoML/pull/5007
- docs: Add CUDA version notes by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5004
- docs: Add new project examples by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5010
- docs: Clean up examples by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5011
- docs: Update adaptive batching doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5012
- docs: Refactor more examples section by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5014
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/5009
- feat: upload setup.sh to the remote dev by @frostming in https://github.com/bentoml/BentoML/pull/5016
- feat: always make an HTTP call when calling self API methods by @frostming in https://github.com/bentoml/BentoML/pull/5017
- feat: gradio integration by @parano in https://github.com/bentoml/BentoML/pull/5008
- Fix a typo by @snowsky in https://github.com/bentoml/BentoML/pull/5018
- docs: Add quotation marks to python versions by @Sherlock113 in https://github.com/bentoml/BentoML/pull/5019
New Contributors
- @snowsky made their first contribution in https://github.com/bentoml/BentoML/pull/5018
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.7...v1.3.8
- Python
Published by frostming over 1 year ago
bentoml - v1.3.6
What's Changed
- doc: include cli commands in secret doc by @ssheng in https://github.com/bentoml/BentoML/pull/4968
- fix: switch back to post-release version scheme by @frostming in https://github.com/bentoml/BentoML/pull/4969
- doc: Add documentation about platform option of bentoml build by @frostming in https://github.com/bentoml/BentoML/pull/4966
- fix: only add bentoml requirement if absent by @frostming in https://github.com/bentoml/BentoML/pull/4973
- fix: null filename causes parsing failure for image input by @frostming in https://github.com/bentoml/BentoML/pull/4976
- doc: add instruction for
bentoml.IODescriptorby @frostming in https://github.com/bentoml/BentoML/pull/4975 - chore: update login error message by @xianml in https://github.com/bentoml/BentoML/pull/4952
- chore: remove grpc client by @aarnphm in https://github.com/bentoml/BentoML/pull/4983
- fix: persist trace across internal requests by @frostming in https://github.com/bentoml/BentoML/pull/4982
- feat: expose request id and trace id in request scope by @frostming in https://github.com/bentoml/BentoML/pull/4977
- fix: add secrets in update/apply commands by @xianml in https://github.com/bentoml/BentoML/pull/4985
- feat: development of release 1.4 by @frostming in https://github.com/bentoml/BentoML/pull/4984
- doc: update quick start to use bentoml importing context manager by @frostming in https://github.com/bentoml/BentoML/pull/4986
- fix: make spinner optional for backward compatibility by @frostming in https://github.com/bentoml/BentoML/pull/4987
- fix: don't initialize cloud client until needed by @frostming in https://github.com/bentoml/BentoML/pull/4989
- doc: fix typo in model composition by @ssheng in https://github.com/bentoml/BentoML/pull/4991
- refactor: unify same schema by @frostming in https://github.com/bentoml/BentoML/pull/4988
- fix(framework): export unsloth lazily by @aarnphm in https://github.com/bentoml/BentoML/pull/4992
- fix: compare bento manifest and dependency client by @frostming in https://github.com/bentoml/BentoML/pull/4993
- fix: structure bento manifest by @frostming in https://github.com/bentoml/BentoML/pull/4994
- fix: allow setting timeout for cloud client; hf api; manifest eq by @frostming in https://github.com/bentoml/BentoML/pull/4995
- fix: with_defaults for docker option and show diff report for bento manifest comparison by @frostming in https://github.com/bentoml/BentoML/pull/4996
- docs: Add ShieldGemma example doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4997
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.5...v1.3.6
- Python
Published by frostming over 1 year ago
bentoml - v1.3.5
What's Changed
- chore(ci): release workflow fix by @frostming in https://github.com/bentoml/BentoML/pull/4962
- fix: ondeployment failed to run for servegrpc by @frostming in https://github.com/bentoml/BentoML/pull/4963
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.4...v1.3.5
- Python
Published by frostming over 1 year ago
bentoml - v1.3.4post1
What's Changed
- chore(ci): release workflow fix by @frostming in https://github.com/bentoml/BentoML/pull/4962
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.4...v1.3.4post1
- Python
Published by frostming over 1 year ago
bentoml - v1.3.4
What's Changed
- fix: don't use temporary directory for temp bento copying by @sauyon in https://github.com/bentoml/BentoML/pull/4938
- refactor: path spec ignore pattern checks children files only by @frostming in https://github.com/bentoml/BentoML/pull/4939
- fix: improve exception handling for pynvml by @rlleshi in https://github.com/bentoml/BentoML/pull/4943
- doc: update cloud deploy with yaml guide by @ssheng in https://github.com/bentoml/BentoML/pull/4944
- doc: fix instructions of http testing by @frostming in https://github.com/bentoml/BentoML/pull/4945
- chore(deps): bump protobufjs from 7.2.4 to 7.2.6 in /grpc-client/node by @dependabot in https://github.com/bentoml/BentoML/pull/4647
- chore(deps): bump transformers from 4.30.0 to 4.38.0 in /examples/inference-graph by @dependabot in https://github.com/bentoml/BentoML/pull/4695
- chore(deps): bump h2 from 0.3.24 to 0.3.26 in /grpc-client/rust by @dependabot in https://github.com/bentoml/BentoML/pull/4635
- chore(deps): bump tar from 6.1.11 to 6.2.1 in /grpc-client/node by @dependabot in https://github.com/bentoml/BentoML/pull/4650
- chore(deps): bump mio from 0.8.8 to 0.8.11 in /grpc-client/rust by @dependabot in https://github.com/bentoml/BentoML/pull/4550
- fix: bentoml.serve to support serving new SDK services from a bento by @frostming in https://github.com/bentoml/BentoML/pull/4946
- docs: Let search engine ignore 1.1 doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4950
- docs: Update readme example links by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4951
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/4953
- fix: don't pull models if already exists when puling bento by @frostming in https://github.com/bentoml/BentoML/pull/4954
- feat: lock packages for linux by default by @frostming in https://github.com/bentoml/BentoML/pull/4955
- chore(deps): bump actions/download-artifact from 3 to 4.1.7 in /.github/workflows in the github_actions group across 1 directory by @dependabot in https://github.com/bentoml/BentoML/pull/4957
- docs: Add function calling example doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4956
- docs: Add a placeholder RAG doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4959
- fix: support pydantic 2.9 by @frostming in https://github.com/bentoml/BentoML/pull/4960
- fix: retry for model and bento upload failure by @frostming in https://github.com/bentoml/BentoML/pull/4961
- fix: reload plugin missing file changes by @frostming in https://github.com/bentoml/BentoML/pull/4958
New Contributors
- @rlleshi made their first contribution in https://github.com/bentoml/BentoML/pull/4943
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.3...v1.3.4
- Python
Published by frostming over 1 year ago
bentoml - v1.3.3
What's Changed
- fix: restore keras.save_model compatibility with Keras 3 by @rmarquis in https://github.com/bentoml/BentoML/pull/4922
- fix(cli): do not hide output behind a spinner for building bento by @frostming in https://github.com/bentoml/BentoML/pull/4923
- feat: expose client url and sync client by @frostming in https://github.com/bentoml/BentoML/pull/4925
- fix: always preserve str and bytes when serializing by @frostming in https://github.com/bentoml/BentoML/pull/4929
- fix(cloud-client): raise error if multipart push fails by @Haivilo in https://github.com/bentoml/BentoML/pull/4932
- feat: Pass torch kwargs to bentoml.pytorch.load_model by @TokeReines in https://github.com/bentoml/BentoML/pull/4930
- docs: Add function calling example link by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4934
- fix: pydantic/numpy patching causes
Cannot interpret 'numpy.float16 | numpy.float32' as a data typeby @frostming in https://github.com/bentoml/BentoML/pull/4933 - fix: uploading large files saving to disk instead of memory by @frostming in https://github.com/bentoml/BentoML/pull/4935
New Contributors
- @rmarquis made their first contribution in https://github.com/bentoml/BentoML/pull/4922
- @TokeReines made their first contribution in https://github.com/bentoml/BentoML/pull/4930
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.2...v1.3.3
- Python
Published by frostming almost 2 years ago
bentoml - v1.3.2
What's Changed
- fix: press text by @xianml in https://github.com/bentoml/BentoML/pull/4898
- ci: pre-commit autoupdate by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/4897
- docs: Update doc images by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4901
- fix: fix resource type by @FogDong in https://github.com/bentoml/BentoML/pull/4904
- fix: direct return response if tracer id is null by @FogDong in https://github.com/bentoml/BentoML/pull/4899
- docs: update azure byoc instructions by @ssheng in https://github.com/bentoml/BentoML/pull/4905
- fix: metrics duration defined with min,max,factor not taking effect by @frostming in https://github.com/bentoml/BentoML/pull/4903
- refactor: store the cloud context into the container instead of passing it around by @frostming in https://github.com/bentoml/BentoML/pull/4907
- docs: Update README.md by @parano in https://github.com/bentoml/BentoML/pull/4906
- docs: Update messages by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4910
- docs: Update index.rst by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4913
- doc: update the HTTP behavior test instruction by @frostming in https://github.com/bentoml/BentoML/pull/4915
- docs: Add metrics doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4912
- feat(cli): reload option for start-http-server by @frostming in https://github.com/bentoml/BentoML/pull/4916
- chore: update pdm.lock file witht the lock targets by @frostming in https://github.com/bentoml/BentoML/pull/4911
- fix(build): preserve the index url options in requirements.txt file by @frostming in https://github.com/bentoml/BentoML/pull/4914
- fix: try to fix the timeout test cases by @frostming in https://github.com/bentoml/BentoML/pull/4917
- doc: update CI status badge by @frostming in https://github.com/bentoml/BentoML/pull/4918
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.1...v1.3.2
- Python
Published by frostming almost 2 years ago
bentoml - v1.3.1
What's Changed
- docs: Add 2 examples by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4872
- docs: update theme to match branding by @ssheng in https://github.com/bentoml/BentoML/pull/4874
- docs: Add task doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4873
- fix: set prometheus env before importing service by @frostming in https://github.com/bentoml/BentoML/pull/4875
- docs: Add API docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4877
- fix: inject prometheus env from arbiter by @frostming in https://github.com/bentoml/BentoML/pull/4878
- fix: Don't run bentoml.build_bentofile in subprocess by @frostming in https://github.com/bentoml/BentoML/pull/4876
- docs: update azure byoc instructions by @ssheng in https://github.com/bentoml/BentoML/pull/4881
- docs(azure): update azure byoc instructions by @ssheng in https://github.com/bentoml/BentoML/pull/4882
- fix(framework): transformers vs 1.3.0 "TypeError: init() got an unexpected keyword argument 'task'" by @frostming in https://github.com/bentoml/BentoML/pull/4880
- fix: silence git output by @frostming in https://github.com/bentoml/BentoML/pull/4883
- fix: surface config error on bento build by @frostming in https://github.com/bentoml/BentoML/pull/4888
- docs: Refactor tasks doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4890
- Docs: Sync the BYOC doc with blog and update BentoCloud guides index page by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4891
- fix: move user setup to base template to make custom base image work by @frostming in https://github.com/bentoml/BentoML/pull/4893
- fix: Cannot define custom duration histogram buckets via
@bentoml.service(metrics=...)by @frostming in https://github.com/bentoml/BentoML/pull/4895
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.0...v1.3.1
- Python
Published by frostming almost 2 years ago
bentoml - v1.3.0
We are excited to announce the release of BentoML 1.3! Following the feedback received since the launch of 1.2 earlier this year, we are introducing a host of new features and enhancements in 1.3. Below are the key highlights of 1.3 and stay tuned for an upcoming blog post, where we'll provide a detailed exploration of the new features and the driving forces behind the development.
Here are some of the important points to note about 1.3:
1.3ensures full backward compatibility, meaning that Bentos built with1.2will continue to work seamlessly with this release.- We remain committed to supporting
1.2. Critical bug fixes and security updates will be backported to the1.2branch. - The BentoML documentation has been updated with examples and guides for
1.3. More guides will be added in the coming weeks. - BentoCloud supports Bento Deployments from both
1.2and1.3releases of BentoML.
Now, let’s take a look at the major features and enhancements:
🕙 Implemented BentoML task execution
- Introduced the
@bentoml.taskdecorator to set a task endpoint for executing a long-running workload (such as batch processing or video generation). - Added the
.submit()method to both the sync and async clients, which can submit task inputs via the task endpoint and dedicated worker processes constantly monitor task queues for new work to perform. - Full compatibility with BentoCloud to run Bentos defined with task endpoints.
- See the Services and Clients doc with examples of a Service API by initializing a long running task in the Service constructor, creating clients to call the endpoint, and retrieving task status.
🚀 Optimized the build cache to accelerate the build process
- Enhanced build speed for
bentoml build&containerizethrough pre-installed large packages liketorch - Switch to
uvas the installer and resolver, replacingpip
🔨 Supported concurrency-based autoscaling on BentoCloud
- Added the
concurrencyconfiguration to the@bentoml.servicedecorator to set the ideal number of simultaneous requests a Service is designed to handle. - Added the
external_queueconfiguration to the@bentoml.servicedecorator to queue excess requests until they can be processed within the definedconcurrencylimits. - See the documentation to configure concurrency and external queue.
🔒 Secure data handling with secrets in BentoCloud:
- You can now create and manage credentials, such as HuggingFace tokens and AWS secrets, securely on BentoCloud and easily apply them across multiple Deployments.
- Added secret subcommands to the BentoML CLI for secret management. Run
bentoml secret -hto learn more.
🗒️ Added streamed logs for Bento image deployment.
- Easier to troubleshoot build issues and enable faster development iterations
🙏 Thank you for your continued support!
What's Changed
- fix: change forbid extra keys to false for bentocloud by @FogDong in https://github.com/bentoml/BentoML/pull/4866
- feat(dev): 1.3 by @frostming in https://github.com/bentoml/BentoML/pull/4849
- fix: delete cluster and ns if it is first cluster by @FogDong in https://github.com/bentoml/BentoML/pull/4869
- fix: auto login confirm ask logic by @xianml in https://github.com/bentoml/BentoML/pull/4864
- fix: secret default value by @xianml in https://github.com/bentoml/BentoML/pull/4870
- fix: fix typo in error msg by @FogDong in https://github.com/bentoml/BentoML/pull/4871
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.20...v1.3.0
- Python
Published by frostming almost 2 years ago
bentoml - v1.3.0a3
What's Changed
- fix: don't fail when image pod is not found by @frostming in https://github.com/bentoml/BentoML/pull/4862
- fix: async task response deserialization crash by @frostming in https://github.com/bentoml/BentoML/pull/4865
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.3.0a2...v1.3.0a3
- Python
Published by frostming almost 2 years ago
bentoml - v1.3.0a1
What's Changed
- feat: get_service api for selected frameworks by @frostming in https://github.com/bentoml/BentoML/pull/4782
- feat: cli auto login by @xianml in https://github.com/bentoml/BentoML/pull/4817
- feat: use rich.print to replace click.echo by @frostming in https://github.com/bentoml/BentoML/pull/4827
- chore: update print and fix cors error by @xianml in https://github.com/bentoml/BentoML/pull/4829
- feat: login to current context instead of default context if --context is not passed by @frostming in https://github.com/bentoml/BentoML/pull/4828
- feat: switch to uv as the resolver and installer by @frostming in https://github.com/bentoml/BentoML/pull/4822
- feat: Officially support Python 3.12 by @frostming in https://github.com/bentoml/BentoML/pull/4830
- Docs: Add auto cli login docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4844
- feat: retry and cancel task by @frostming in https://github.com/bentoml/BentoML/pull/4852
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.20...v1.3.0a1
- Python
Published by frostming almost 2 years ago
bentoml - v1.2.20
What's Changed
- docs: Add logging and tracing docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4725
- feat: --label option for bentoml build by @frostming in https://github.com/bentoml/BentoML/pull/4832
- docs: Update the concurrency doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4834
- docs: Update services.rst by @vikramjit-sidhu in https://github.com/bentoml/BentoML/pull/4837
- docs: Update concurrency links by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4840
- docs: Fix broken link by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4841
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/4838
- fix: stop spinner before starting to stream logs by @frostming in https://github.com/bentoml/BentoML/pull/4846
- docs: Add azure byoc setup doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4847
- docs: Update the BYOC architecture image by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4848
- fix: fix error message with trace id by @FogDong in https://github.com/bentoml/BentoML/pull/4853
- doc: locking by @bojiang in https://github.com/bentoml/BentoML/pull/4850
- fix(containerize): command to create group and user in alpine base image by @frostming in https://github.com/bentoml/BentoML/pull/4855
- fix: encode special charaters in path by @frostming in https://github.com/bentoml/BentoML/pull/4854
- doc: locking for platform by @frostming in https://github.com/bentoml/BentoML/pull/4858
- fix: correct the params passed to keras.save_model by @frostming in https://github.com/bentoml/BentoML/pull/4857
New Contributors
- @vikramjit-sidhu made their first contribution in https://github.com/bentoml/BentoML/pull/4837
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.19...v1.2.20
- Python
Published by frostming almost 2 years ago
bentoml - v1.2.19
What's Changed
- docs: Update diffusion model repos to the new one by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4797
- feat(monitoring): support GRPC LogExporter by @judahrand in https://github.com/bentoml/BentoML/pull/4808
- docs: Add Docker deployment for Bentos by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4812
- docs: update examples service decorators with new features by @ssheng in https://github.com/bentoml/BentoML/pull/4798
- doc: Custom Error Handling by @jianshen92 in https://github.com/bentoml/BentoML/pull/4811
- doc: Wording change in error handling doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4813
- fix: ASCII animation was not working properly in the image builder logs by @yetone in https://github.com/bentoml/BentoML/pull/4810
- fix: avoid editing list in during iteration by @judahrand in https://github.com/bentoml/BentoML/pull/4809
- docs: Add secrets doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4814
- fix: improve the code of spinner and log tailer by @frostming in https://github.com/bentoml/BentoML/pull/4815
- doc: Update the docs about multipart output by @frostming in https://github.com/bentoml/BentoML/pull/4818
- docs: Add batch inference jobs doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4816
- doc: Fix typo and format by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4821
- fix(cli): hanging issue when deployment ready by @frostming in https://github.com/bentoml/BentoML/pull/4825
- fix(deployment-client): add build process and extend url by @Haivilo in https://github.com/bentoml/BentoML/pull/4790
- doc: Update vllm.rst by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4824
- docs: Add custom models use case doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4819
- docs: Reorg blip doc to multimodality section by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4826
- fix: inject prometheus multiproc_dir into env var when worker starts by @frostming in https://github.com/bentoml/BentoML/pull/4820
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.18...v1.2.19
- Python
Published by frostming almost 2 years ago
bentoml - v1.2.18
What's Changed
- docs: scale from zero by @ssheng in https://github.com/bentoml/BentoML/pull/4769
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/4772
- docs: Update installation.rst by @parano in https://github.com/bentoml/BentoML/pull/4763
- docs: Add chatTTS to example project list by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4777
- fix: bad performance when walking the file tree and check includes by @frostming in https://github.com/bentoml/BentoML/pull/4778
- update readme to include chattts by @ssheng in https://github.com/bentoml/BentoML/pull/4786
- docs: Update README.md by @parano in https://github.com/bentoml/BentoML/pull/4785
- Fixed
FileExistsError: [Errno 17] File exists: '/root/bentoml'by @tripathiarpan20 in https://github.com/bentoml/BentoML/pull/4781 - fix: set env to null if it is empty for merge override by @FogDong in https://github.com/bentoml/BentoML/pull/4783
- fix: add none check for env for deploy by @FogDong in https://github.com/bentoml/BentoML/pull/4792
- fix(pandas): use correct mime type for Parquet by @judahrand in https://github.com/bentoml/BentoML/pull/4780
- fix: add memoization to
pkg_version_infoto reduce cpu overhead by @adrianlyjak in https://github.com/bentoml/BentoML/pull/4794 - fix: bug: memory leak when using bentoml>=1.2 by @frostming in https://github.com/bentoml/BentoML/pull/4775
- fix: honor host and port config in service decorator by @frostming in https://github.com/bentoml/BentoML/pull/4776
- fix(pandas):
Annotated[pd.DataFrame, DataframeSchema(columns=["a"])]output spec by @judahrand in https://github.com/bentoml/BentoML/pull/4799 - fix: ensure relative path works within bento project by @aarnphm in https://github.com/bentoml/BentoML/pull/4803
- fix: map error responses from HTTP client to bentoml exceptions by @frostming in https://github.com/bentoml/BentoML/pull/4804
- fix(numpy):
numpyannotation processing by @judahrand in https://github.com/bentoml/BentoML/pull/4795 - fix: populate bento name and version of server context by @frostming in https://github.com/bentoml/BentoML/pull/4787
- fix(cloud-client): consider httpcore timeout when getting status by @Haivilo in https://github.com/bentoml/BentoML/pull/4740
- fix: cd into src instead of bento parent by @frostming in https://github.com/bentoml/BentoML/pull/4805
- feat: show image builder logs by @yetone in https://github.com/bentoml/BentoML/pull/4796
New Contributors
- @tripathiarpan20 made their first contribution in https://github.com/bentoml/BentoML/pull/4781
- @adrianlyjak made their first contribution in https://github.com/bentoml/BentoML/pull/4794
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.17...v1.2.18
- Python
Published by frostming almost 2 years ago
bentoml - v1.2.17
What's Changed
- docs: update model store by @ssheng in https://github.com/bentoml/BentoML/pull/4741
- docs: Add env var for mistral 7b docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4747
- refactor(tests): testing.util.async_request to client.AsyncHTTPClient by @sanspareilsmyn in https://github.com/bentoml/BentoML/pull/4746
- docs: Update GitHub readme by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4749
- chore(build): update build_config.py by @eltociear in https://github.com/bentoml/BentoML/pull/4751
- docs: Add git package packing doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4750
- fix: configure server logging before importing service by @frostming in https://github.com/bentoml/BentoML/pull/4744
- docs: Add user roles docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4724
- feat(batching): break batch into smaller partitions if it's larger than max batch size by @frostming in https://github.com/bentoml/BentoML/pull/4752
- docs: Update the examples folder readme by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4748
- docs: Add byoc setup docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4757
- fix: new sdk e2e test by @xianml in https://github.com/bentoml/BentoML/pull/4758
- fix: metrics did not include 4xx by @xianml in https://github.com/bentoml/BentoML/pull/4756
- fix: should enable existing loggers in server logging config by @rickzx in https://github.com/bentoml/BentoML/pull/4759
- fix: client response deserialization when the output is string by @frostming in https://github.com/bentoml/BentoML/pull/4762
- fix: middleware reorder by @xianml in https://github.com/bentoml/BentoML/pull/4761
- fix: log errors inside a streaming response and detect service name conflicts by @frostming in https://github.com/bentoml/BentoML/pull/4767
- fix: don't try to validate non-bytes as Path by @frostming in https://github.com/bentoml/BentoML/pull/4765
New Contributors
- @sanspareilsmyn made their first contribution in https://github.com/bentoml/BentoML/pull/4746
- @eltociear made their first contribution in https://github.com/bentoml/BentoML/pull/4751
- @rickzx made their first contribution in https://github.com/bentoml/BentoML/pull/4759
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.16...v1.2.17
- Python
Published by frostming almost 2 years ago
bentoml - v1.2.16
What's Changed
- fix(build): make sure to parse pip_args in correct order by @aarnphm in https://github.com/bentoml/BentoML/pull/4722
- docs: Add compound data types doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4721
- docs: Add docs for installing GitHub packages for Bento by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4720
- docs: Update deployment details explanations by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4726
- fix: load model aliases before loading new SDK service by @frostming in https://github.com/bentoml/BentoML/pull/4727
- docs: Fix cpu as strings by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4735
- docs: Update the services doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4734
- feat: add trace id to monitoring module by @jianshen92 in https://github.com/bentoml/BentoML/pull/4732
- feat: add a switch to opt-out packing git packages by @frostming in https://github.com/bentoml/BentoML/pull/4729
- fix: missing components from output schema if it is a root model by @frostming in https://github.com/bentoml/BentoML/pull/4733
- feat: expose the service url as a property by @frostming in https://github.com/bentoml/BentoML/pull/4730
- fix(container): preheat packages support markers by @bojiang in https://github.com/bentoml/BentoML/pull/4737
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.15...v1.2.16
- Python
Published by frostming about 2 years ago
bentoml - v1.2.14
What's Changed
- fix: add scaled to zero in client by @FogDong in https://github.com/bentoml/BentoML/pull/4712
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/4713
- fix: serailization error when request with an invalid json input by @frostming in https://github.com/bentoml/BentoML/pull/4714
- fix: config pollution from other services by @frostming in https://github.com/bentoml/BentoML/pull/4715
- fix: handle ssh git url without ref part by @frostming in https://github.com/bentoml/BentoML/pull/4716
- fix: correct the default value of timeout-keep-alive by @frostming in https://github.com/bentoml/BentoML/pull/4717
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.13...v1.2.14
- Python
Published by frostming about 2 years ago
bentoml - v1.2.13
What's Changed
- docs: fix indentation in build option docs by @jianshen92 in https://github.com/bentoml/BentoML/pull/4688
- fix: bug: module 'bentoml' has no attribute 'build' by @frostming in https://github.com/bentoml/BentoML/pull/4689
- docs: update autoscaling by @ssheng in https://github.com/bentoml/BentoML/pull/4691
- docs: init io-descriptors example by @lycheel1 in https://github.com/bentoml/BentoML/pull/4646
- fix: uncaught error missing trace headers by @frostming in https://github.com/bentoml/BentoML/pull/4692
- chore: remove outdated examples by @larme in https://github.com/bentoml/BentoML/pull/4694
- fix: bypass /livez in traffic middleware by @frostming in https://github.com/bentoml/BentoML/pull/4696
- docs:Update credits by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4700
- docs: Add model store reference in the Services doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4706
- docs: Update example dir readme by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4707
- fix: fix table overflow with fold by @FogDong in https://github.com/bentoml/BentoML/pull/4677
- fix: server socket binding on Windows by @frostming in https://github.com/bentoml/BentoML/pull/4685
- fix: correct the logic of bypassing infra endpoints in traffic middleware by @frostming in https://github.com/bentoml/BentoML/pull/4704
- fix: add scaled to zero to ready status by @FogDong in https://github.com/bentoml/BentoML/pull/4708
- chore(container): cache large pypi packages in layers by @bojiang in https://github.com/bentoml/BentoML/pull/4690
- feat: add uvicorn timeouts options by @gusghrlrl101 in https://github.com/bentoml/BentoML/pull/4682
- fix: include models from config for new SDK bentos by @frostming in https://github.com/bentoml/BentoML/pull/4705
- fix: annotation preparation list iteration bug by @adamliter in https://github.com/bentoml/BentoML/pull/4701
- fix: tuple schema and websocket connection by @frostming in https://github.com/bentoml/BentoML/pull/4709
- fix: show warning instead of hard failure when model is missing by @frostming in https://github.com/bentoml/BentoML/pull/4693
New Contributors
- @gusghrlrl101 made their first contribution in https://github.com/bentoml/BentoML/pull/4682
- @adamliter made their first contribution in https://github.com/bentoml/BentoML/pull/4701
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.12...v1.2.13
- Python
Published by frostming about 2 years ago
bentoml - v1.2.12
What's Changed
- docs: Add GPU inference doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4654
- chore: update quickstart by @ssheng in https://github.com/bentoml/BentoML/pull/4655
- docs: Add JSON output for bentovllm by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4657
- chore: cleanup quickstart by @ssheng in https://github.com/bentoml/BentoML/pull/4658
- docs: Update help info by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4664
- fix: remove the uvicorn server header by @frostming in https://github.com/bentoml/BentoML/pull/4665
- docs: Fix format by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4666
- docs: Add model composition doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4668
- docs: Update example project list by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4673
- docs: Add the monitoring and data collection doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4662
- docs: Add addasgimiddleware doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4672
- fix: delete useless enum and fix enum value by @FogDong in https://github.com/bentoml/BentoML/pull/4674
- docs: Add RAG tutorial by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4675
- docs: Update the clients doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4676
- docs: Add some explanations for bentoml.models.get by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4660
- docs: Add e2e test doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4679
- fix(cloud client): various type error by @bojiang in https://github.com/bentoml/BentoML/pull/4680
- fix(cli): bentoml cli verbosity not passed to the subprocess correctly by @frostming in https://github.com/bentoml/BentoML/pull/4661
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.11...v1.2.12
- Python
Published by bojiang about 2 years ago
bentoml - v1.2.11
What's Changed
- docs: added multi model load and store example by @lycheel1 in https://github.com/bentoml/BentoML/pull/4575
- docs: inference graph by @lycheel1 in https://github.com/bentoml/BentoML/pull/4609
- docs: Update high-level BentoML messaging by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4644
- fix: delete trace error for timeout when deploying by @FogDong in https://github.com/bentoml/BentoML/pull/4649
- fix(cli): correct the comparison of upload status by @frostming in https://github.com/bentoml/BentoML/pull/4643
New Contributors
- @lycheel1 made their first contribution in https://github.com/bentoml/BentoML/pull/4575
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.10...v1.2.11
- Python
Published by frostming about 2 years ago
bentoml - v1.2.10
What's Changed
- docs: Remove old example links by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4610
- feat(build): use jinja template for install script by @aarnphm in https://github.com/bentoml/BentoML/pull/4607
- feat: download git+ssh dependencies to wheels/ folder by @frostming in https://github.com/bentoml/BentoML/pull/4612
- docs: Update the ASGI doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4614
- fix: non batched request executed in non FIFO manner by @frostming in https://github.com/bentoml/BentoML/pull/4619
- feat: light-weighted dev sdist builder by @frostming in https://github.com/bentoml/BentoML/pull/4615
- fix: add response headers for error responses by @frostming in https://github.com/bentoml/BentoML/pull/4622
- docs: Refactor the autoscaling doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4620
- docs: Add simple verification test for Services by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4629
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/4630
- docs: Add workers doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4628
- docs: Add worker doc links by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4636
- docs: Add docs for bentoml.runner_service by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4637
- docs: Add sync to async doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4639
- fix: handle call on clients by @frostming in https://github.com/bentoml/BentoML/pull/4618
- fix(cli):
bentoml getoutput in YAML format by @frostming in https://github.com/bentoml/BentoML/pull/4638 - fix: issue overriding default service config from config file by @frostming in https://github.com/bentoml/BentoML/pull/4627
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.9...v1.2.10
- Python
Published by frostming about 2 years ago
bentoml - v1.2.9
What's Changed
- docs: add autoscaling docs by @ssheng in https://github.com/bentoml/BentoML/pull/4601
- docs: Fix old configurations doc link by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4600
- docs: Update the concurrency doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4602
- fix(reload): make sure to watch for all src for editable by @aarnphm in https://github.com/bentoml/BentoML/pull/4604
- fix(openapi): remove invalid fields for operations parameter by @aarnphm in https://github.com/bentoml/BentoML/pull/4605
- chore: update swagger UI generated to 5.12 [skip ci] by @aarnphm in https://github.com/bentoml/BentoML/pull/4606
- fix(cloud cli): workaround env update issue by @bojiang in https://github.com/bentoml/BentoML/pull/4608
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.8...v1.2.9
- Python
Published by bojiang about 2 years ago
bentoml - v1.2.8
What's Changed
- fix(stub): add envs to
__init__construction by @aarnphm in https://github.com/bentoml/BentoML/pull/4576 - docs: Add testing doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4578
- chore(type): use TypedDict for inferred stubs by @aarnphm in https://github.com/bentoml/BentoML/pull/4577
- docs: Add lifecycle hooks doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4579
- fix(build): remove deprecated warnings by @aarnphm in https://github.com/bentoml/BentoML/pull/4580
- fix: improve the bentoml build progress by @frostming in https://github.com/bentoml/BentoML/pull/4582
- fix: allow API endpoint to return response directly by @frostming in https://github.com/bentoml/BentoML/pull/4581
- fix: raise the priority of the routes from mount apps by @frostming in https://github.com/bentoml/BentoML/pull/4584
- fix(sdk): python build missing envs argument by @jianshen92 in https://github.com/bentoml/BentoML/pull/4585
- fix: build config env default to None by @jianshen92 in https://github.com/bentoml/BentoML/pull/4589
- fix: config from multiple services override with each other by @frostming in https://github.com/bentoml/BentoML/pull/4591
- feat: add concurrency config by @xianml in https://github.com/bentoml/BentoML/pull/4560
- docs: Add OpenAI compatible endpoints client doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4593
- fix: ignoreextrakeys for v2 configuration schema by @xianml in https://github.com/bentoml/BentoML/pull/4598
- fix: emit warnings when copying large file by @frostming in https://github.com/bentoml/BentoML/pull/4597
- feat: service.to_async property by @frostming in https://github.com/bentoml/BentoML/pull/4595
- feat: picklev5 serialization by @frostming in https://github.com/bentoml/BentoML/pull/4594
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.7...v1.2.8
- Python
Published by frostming about 2 years ago
bentoml - v1.2.7
What's Changed
- docs: Add doc for serverreadytimeout by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4563
- fix: depracate all enum in schema by @FogDong in https://github.com/bentoml/BentoML/pull/4565
- feat: threaded serving by @frostming in https://github.com/bentoml/BentoML/pull/4562
- docs: Adjust existing Bento deployment wording by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4567
- fix: fix list instance type by @FogDong in https://github.com/bentoml/BentoML/pull/4566
- docs: Add doc for using pydantic model at the top level by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4568
- fix: delete access in admin console by @FogDong in https://github.com/bentoml/BentoML/pull/4569
- fix(client): set upload timeouts to 10 hours by @sauyon in https://github.com/bentoml/BentoML/pull/4564
- fix: respect the content type config for file output by @frostming in https://github.com/bentoml/BentoML/pull/4570
- docs: Update the adaptive batching doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4571
- feat: Service.to_asgi() method by @frostming in https://github.com/bentoml/BentoML/pull/4572
- docs: Add asgi doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4574
- fix: allow legacy runnable methods when calling API by @frostming in https://github.com/bentoml/BentoML/pull/4573
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.6...v1.2.7
- Python
Published by frostming about 2 years ago
bentoml - v1.2.6
What's Changed
- docs: Add envs field in bentofile by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4555
- docs: Add GitHub repo links for use case docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4556
- docs: Update the vllm use case doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4558
- docs: Add how to get deployment info doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4544
- fix: rename the bentomlsdk.api module by @frostming in https://github.com/bentoml/BentoML/pull/4557
- fix: wait until server ready when initializing client by @frostming in https://github.com/bentoml/BentoML/pull/4559
- feat: Add server.on_deployment hook to execute deployment-specific logic by @frostming in https://github.com/bentoml/BentoML/pull/4561
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.5...v1.2.6
- Python
Published by frostming about 2 years ago
bentoml - v1.2.5
What's Changed
- docs: Add client code examples without context manager by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4512
- docs: Update docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4515
- docs: Add authorization docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4517
- docs: Change sample input to one line by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4518
- docs: Update ControlNet use case docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4519
- docs: Update the distributed services and get started docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4521
- refactor(cli): make CLI commands available as modules by @frostming in https://github.com/bentoml/BentoML/pull/4487
- docs: Refactor BentoCloud docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4525
- docs: Update token docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4526
- fix: fix list deployment exception by @FogDong in https://github.com/bentoml/BentoML/pull/4522
- feat: add get endpoint url for deployment by @FogDong in https://github.com/bentoml/BentoML/pull/4516
- docs: Add BentoCloud CLI and API ref docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4527
- fix: add missing to dict for deployment config by @FogDong in https://github.com/bentoml/BentoML/pull/4529
- feat(client): disallow media type other than json for HTTP clients by @frostming in https://github.com/bentoml/BentoML/pull/4520
- chore: clean unneeded dependencies by @frostming in https://github.com/bentoml/BentoML/pull/4528
- docs: Add call deployment endpoints doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4531
- docs: Update all use cases by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4532
- fix: correctly encode ValueError in response by @frostming in https://github.com/bentoml/BentoML/pull/4530
- fix: improve CLI message by @frostming in https://github.com/bentoml/BentoML/pull/4533
- chore(io): allow implicit pydantic type conversion by @aarnphm in https://github.com/bentoml/BentoML/pull/4534
- fix: type convertion of io descriptor by @frostming in https://github.com/bentoml/BentoML/pull/4537
- feat: add back service hooks by @frostming in https://github.com/bentoml/BentoML/pull/4524
- docs: fix typo by @sauyon in https://github.com/bentoml/BentoML/pull/4540
- docs: Add BentoSVD Use case doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4535
- doc: Add adaptive batching doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4536
- doc: allow reuse of existing directory by @jianshen92 in https://github.com/bentoml/BentoML/pull/4543
- feat: cloud context from env vars by @frostming in https://github.com/bentoml/BentoML/pull/4542
- docs: Update the clients doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4539
- docs: Update adaptive batching docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4547
- docs: Update vLLM use case doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4548
- feat: export component context at top namespace by @frostming in https://github.com/bentoml/BentoML/pull/4551
- feat: use starlette request directly in service context by @frostming in https://github.com/bentoml/BentoML/pull/4552
- feat: mount asgi app and fastapi support by @frostming in https://github.com/bentoml/BentoML/pull/4538
- fix(sdk): build envs into dockerfile by @bojiang in https://github.com/bentoml/BentoML/pull/4546
- fix: rename server context attributes by @frostming in https://github.com/bentoml/BentoML/pull/4553
- fix: crash when pulling bento from organization with proxy mode by @frostming in https://github.com/bentoml/BentoML/pull/4554
- fix: add str in enum for deployment schema by @FogDong in https://github.com/bentoml/BentoML/pull/4549
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.4...v1.2.5
- Python
Published by frostming about 2 years ago
bentoml - v1.2.4
What's Changed
- docs: Update the get started docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4513
- fix(sdk): incorrect bento_path if not provided by @bojiang in https://github.com/bentoml/BentoML/pull/4514
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.3...v1.2.4
- Python
Published by bojiang over 2 years ago
bentoml - v1.2.3
What's Changed
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/4488
- infra: update to use Ruff formatter by @aarnphm in https://github.com/bentoml/BentoML/pull/4269
- feat: tpu_type support by @frostming in https://github.com/bentoml/BentoML/pull/4493
- chore(cloud cli): add cluster and expose access_point by @bojiang in https://github.com/bentoml/BentoML/pull/4490
- docs: Update the whisperx use case by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4495
- docs: Update the readme by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4496
- fix(sdk): current directory for built bentos by @bojiang in https://github.com/bentoml/BentoML/pull/4505
- chore(cloud cli): rename cluster to region by @bojiang in https://github.com/bentoml/BentoML/pull/4508
- doc: Add the lcm lora use case doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4510
- fix(sdk): clean bentoml version by @bojiang in https://github.com/bentoml/BentoML/pull/4511
- fix: bug: Dataframes not serializing correctly in the new API by @frostming in https://github.com/bentoml/BentoML/pull/4491
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.2...v1.2.3
- Python
Published by ssheng over 2 years ago
bentoml - v1.2.2
What's Changed
- docs: Remove direct execution lines by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4480
- docs: Refactor deployment docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4482
- docs: Add build options doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4483
- feat: lock dependencies by default considering the current bentoml version by @frostming in https://github.com/bentoml/BentoML/pull/4484
- docs: Add distributed services doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4485
- fix(server): clean the request resources after the response is consumed by @frostming in https://github.com/bentoml/BentoML/pull/4481
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.1...v1.2.2
- Python
Published by frostming over 2 years ago
bentoml - v1.2.1
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.1a1...v1.2.1
What's Changed
- docs: Add more featured use cases by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4476
- docs: Add API reference doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4475
- docs: Clean API ref docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4477
- fix: fix the cluster from display name to name and url by @FogDong in https://github.com/bentoml/BentoML/pull/4478
- fix(cli): add start runner server back by @bojiang in https://github.com/bentoml/BentoML/pull/4479
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.0...v1.2.1
- Python
Published by bojiang over 2 years ago
bentoml - v1.2.1a1
What's Changed
- docs: Add more featured use cases by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4476
- docs: Add API reference doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4475
- docs: Clean API ref docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4477
- fix: fix the cluster from display name to name and url by @FogDong in https://github.com/bentoml/BentoML/pull/4478
- fix(cli): add start runner server back by @bojiang in https://github.com/bentoml/BentoML/pull/4479
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.0...v1.2.1a1
- Python
Published by bojiang over 2 years ago
bentoml - v1.2.0
What's Changed
- chore(deps): bump h2 from 0.3.20 to 0.3.24 in /grpc-client/rust by @dependabot in https://github.com/bentoml/BentoML/pull/4434
- fix: Remove trailing character when building bento with API on Windows by @holzweber in https://github.com/bentoml/BentoML/pull/4455
- fix: Replace backslahes by normal slashes, making bentoml pull possible on windows by @holzweber in https://github.com/bentoml/BentoML/pull/4456
- fix(monitoring): Missing f string by @jianshen92 in https://github.com/bentoml/BentoML/pull/4463
- feat: 1.2 staging by @bojiang in https://github.com/bentoml/BentoML/pull/4366
- chore(deps): bump pdm-project/setup-pdm from 3 to 4 by @dependabot in https://github.com/bentoml/BentoML/pull/4457
- fix(client): Convert string to Path if it isn't like a URL by @frostming in https://github.com/bentoml/BentoML/pull/4469
- docs: Add Model Store doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4471
- docs: Clean up BentoCloud doc and add get started doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4472
- docs: Update the quickstart by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4474
New Contributors
- @holzweber made their first contribution in https://github.com/bentoml/BentoML/pull/4455
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.0rc1...v1.2.0
- Python
Published by ssheng over 2 years ago
bentoml - v1.2.0rc1
What's Changed
- fix: correct schema for optional type by @frostming in https://github.com/bentoml/BentoML/pull/4459
- fix: client sending request fail if the input is a list of files by @frostming in https://github.com/bentoml/BentoML/pull/4461
- fix: worker number of start-http-server by @bojiang in https://github.com/bentoml/BentoML/pull/4462
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.0a7...v1.2.0rc1
- Python
Published by frostming over 2 years ago
bentoml - v1.2.0a6
What's Changed
- feat: add adaptive batch size histogram by @frostming in https://github.com/bentoml/BentoML/pull/4438
- ci: Use nox as the task runner by @frostming in https://github.com/bentoml/BentoML/pull/4432
- feat(cli): remove or hide unneeded commands by @frostming in https://github.com/bentoml/BentoML/pull/4441
- docs: Add whisperx use case doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4436
- docs: Add Docker deployment doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4443
- docs: Add io types doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4444
- fix: only inline display images by @frostming in https://github.com/bentoml/BentoML/pull/4442
- docs: Update homepage by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4445
- feat: skip access log for infra endpoints by @frostming in https://github.com/bentoml/BentoML/pull/4447
- feat: add schema in bentoInfo by @xianml in https://github.com/bentoml/BentoML/pull/4439
- fix: fix deployment cli log by @FogDong in https://github.com/bentoml/BentoML/pull/4450
- fix: convert generator to async gen before response by @frostming in https://github.com/bentoml/BentoML/pull/4448
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.0a5...v1.2.0a6
- Python
Published by frostming over 2 years ago
bentoml - v1.2.0a4
What's Changed
- fix: make client timeout consistent with service config by @frostming in https://github.com/bentoml/BentoML/pull/4425
- fix: fix env in deploy and create error msg by @FogDong in https://github.com/bentoml/BentoML/pull/4426
- fix: port reservation causes bind error on Windows by @frostming in https://github.com/bentoml/BentoML/pull/4427
- fix: add more status check in wait until ready by @FogDong in https://github.com/bentoml/BentoML/pull/4428
- fix: use spinner log instead of console log by @FogDong in https://github.com/bentoml/BentoML/pull/4429
- fix: add config dict to cli by @FogDong in https://github.com/bentoml/BentoML/pull/4424
- docs: Add client and use case docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4430
- fix(sdk): snake case bento names by @bojiang in https://github.com/bentoml/BentoML/pull/4431
- docs: Add SDXL turbo use case by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4433
- docs: Update readme doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4409
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.0a3...v1.2.0a4
- Python
Published by frostming over 2 years ago
bentoml - v1.2.0a3
What's Changed
- fix(server): start-http-server for v1.0 bentos by @bojiang in https://github.com/bentoml/BentoML/pull/4421
- fix: refactor cli & sdk for deployment by @FogDong in https://github.com/bentoml/BentoML/pull/4419
- fix: fix get bento from cloud by @FogDong in https://github.com/bentoml/BentoML/pull/4423
- fix: change entry_service to optional by @xianml in https://github.com/bentoml/BentoML/pull/4422
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.0a2...v1.2.0a3
- Python
Published by frostming over 2 years ago
bentoml - v1.2.0a2
What's Changed
- feat: allow url as file input by @frostming in https://github.com/bentoml/BentoML/pull/4411
- fix(sdk): validate service name; force lowercase by @bojiang in https://github.com/bentoml/BentoML/pull/4414
- refactor(bento): add entry_service to bento info by @bojiang in https://github.com/bentoml/BentoML/pull/4417
- fix: set content type from annotation by @frostming in https://github.com/bentoml/BentoML/pull/4416
- fix(server): include system headers by @bojiang in https://github.com/bentoml/BentoML/pull/4418
- fix: loading service from an absolute path by @frostming in https://github.com/bentoml/BentoML/pull/4415
- docs: Add BLIP, CLIP, and sentence embedding use cases by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4420
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.0a1...v1.2.0a2
- Python
Published by frostming over 2 years ago
bentoml - v1.2.0a1
What's Changed
- fix(docs): remove eager type evaluation for python 3.8 on openllm examples by @aarnphm in https://github.com/bentoml/BentoML/pull/4393
- docs: fix typo in tritonserver_type parameter and code example by @ilyahabr in https://github.com/bentoml/BentoML/pull/4394
New Contributors
- @ilyahabr made their first contribution in https://github.com/bentoml/BentoML/pull/4394
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.2.0a0...v1.2.0a1
- Python
Published by frostming over 2 years ago
bentoml - v1.2.0a0
What's Changed
- feat: add preview feature for output by @jinyang1994 in https://github.com/bentoml/BentoML/pull/4319
- feat: add feature for form validation by @jinyang1994 in https://github.com/bentoml/BentoML/pull/4322
- fix: example and bento config by @FogDong in https://github.com/bentoml/BentoML/pull/4324
- fix: set wrong default value when type is array by @jinyang1994 in https://github.com/bentoml/BentoML/pull/4332
- feat: add v2 config and json override env by @FogDong in https://github.com/bentoml/BentoML/pull/4331
- feat: config override by @frostming in https://github.com/bentoml/BentoML/pull/4334
- feat: models.save api and tests by @MingLiangDai in https://github.com/bentoml/BentoML/pull/4307
- fix: fix config migration by @FogDong in https://github.com/bentoml/BentoML/pull/4341
- fix: async api call by @xianml in https://github.com/bentoml/BentoML/pull/4349
- fix(config): typo on override by @Haivilo in https://github.com/bentoml/BentoML/pull/4351
- feat: reorganize the new SDK package by @frostming in https://github.com/bentoml/BentoML/pull/4337
- feat: support .python-version symlink by @aarnphm in https://github.com/bentoml/BentoML/pull/4354
- feat: add loading status when form is submitting by @jinyang1994 in https://github.com/bentoml/BentoML/pull/4361
- feat: add e2e tests for new SDK by @frostming in https://github.com/bentoml/BentoML/pull/4352
- fix(with_config): annotate return type by @aarnphm in https://github.com/bentoml/BentoML/pull/4355
- Chore: add supported gpu type by @xianml in https://github.com/bentoml/BentoML/pull/4363
- fix(config): make sure to escape quotation for migration of services config by @aarnphm in https://github.com/bentoml/BentoML/pull/4369
- fix(sdk): identify async by original func by @bojiang in https://github.com/bentoml/BentoML/pull/4370
- chore(bento.yaml): move fields into services by @bojiang in https://github.com/bentoml/BentoML/pull/4372
- fix: add services in manifest by @FogDong in https://github.com/bentoml/BentoML/pull/4373
- chore(sdk): envs in bentofile by @bojiang in https://github.com/bentoml/BentoML/pull/4378
- chore(cloud): include envs in manifest by @bojiang in https://github.com/bentoml/BentoML/pull/4379
- chore: cherry-pick SSE utils into 1.2 branch by @aarnphm in https://github.com/bentoml/BentoML/pull/4375
- fix: correct 1.2 model list and tag format when pushing bento by @Haivilo in https://github.com/bentoml/BentoML/pull/4381
- feat: Update the bento yaml schema by @frostming in https://github.com/bentoml/BentoML/pull/4371
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/4382
- chore(sdk): able to specify service name by @bojiang in https://github.com/bentoml/BentoML/pull/4377
- feat(bentocloud): deployment v2 api client + cli by @Haivilo in https://github.com/bentoml/BentoML/pull/4335
- chore(deps): bump github/codeql-action from 2 to 3 by @dependabot in https://github.com/bentoml/BentoML/pull/4343
- feat(sdk): use attribute chain as dependency import string by @frostming in https://github.com/bentoml/BentoML/pull/4385
- chore(example): change name to avoid conflict by @bojiang in https://github.com/bentoml/BentoML/pull/4387
- refactor(impl): 1.2 loader by @bojiang in https://github.com/bentoml/BentoML/pull/4388
- fix: refactor deployment v2 client and cli by @FogDong in https://github.com/bentoml/BentoML/pull/4383
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.1.11...v1.2.0a0
- Python
Published by frostming over 2 years ago
bentoml - BentoML - v1.1.11
Bug fixes
- Fix streaming for long payloads on remote runners. It will now always yield text and follow SSE protocol. We also provide
SSEutils: ```python import bentoml from bentoml.io import SSE
class MyRunnable(bentoml.Runnable): @bentoml.Runnable.method() def streaming(self, text): yield "data: 1\n\n" yield "data: 12222222222222222222222222222\n\n"
runner = bentoml.Runner(MyRunnable)
svc = bentoml.Service("service", runners=[runner])
@svc.api() def infer(text): result = 0 async for it in runner.streaming.asyncstream(text): payload = SSE.fromiterator(it) result += int(payload.data) return result ```
What's Changed
- docs: Add BentoCloud payment doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4286
- docs: update quickstart with OpenLLM by @aarnphm in https://github.com/bentoml/BentoML/pull/4295
- fix(docs): correct server implementation by @aarnphm in https://github.com/bentoml/BentoML/pull/4297
- docs: Remove bill void status by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4299
- docs: Update LLM quickstart format and wording by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4300
- fix: citation link at
README.mdby @shenxiangzhuang in https://github.com/bentoml/BentoML/pull/4301 - fix(transformers): support
trust_remote_codeand added unit tests by @MingLiangDai in https://github.com/bentoml/BentoML/pull/4271 - docs: Add Bento Deployment details docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4304
- test: remove outdated tests with pretrained_class parameter by @MingLiangDai in https://github.com/bentoml/BentoML/pull/4308
- fix: Updated starlette to >= 0.24.0 by @jakthra in https://github.com/bentoml/BentoML/pull/4306
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/4316
- fix: syntax error on code snippet in bentoml.onnx.save_model docs by @lucasew in https://github.com/bentoml/BentoML/pull/4323
- chore(deps): bump actions/setup-python from 4 to 5 by @dependabot in https://github.com/bentoml/BentoML/pull/4329
- docs: fixed typo in file name benchmark README.md by @gazon1 in https://github.com/bentoml/BentoML/pull/4342
- fix(stream): streaming enable to work with proxy by @jianshen92 in https://github.com/bentoml/BentoML/pull/4330
- docs: fix typo in frameworks transformers guide by @IbrahimAmin1 in https://github.com/bentoml/BentoML/pull/4360
- chore(sse): refactor sse utils with efficient buffering by @bojiang in https://github.com/bentoml/BentoML/pull/4362
- fix(runner): fix DataFrame container header too long by @larme in https://github.com/bentoml/BentoML/pull/4364
- chore(generated): new stubs for proto 4 by @aarnphm in https://github.com/bentoml/BentoML/pull/4374
New Contributors
- @shenxiangzhuang made their first contribution in https://github.com/bentoml/BentoML/pull/4301
- @jakthra made their first contribution in https://github.com/bentoml/BentoML/pull/4306
- @lucasew made their first contribution in https://github.com/bentoml/BentoML/pull/4323
- @gazon1 made their first contribution in https://github.com/bentoml/BentoML/pull/4342
- @IbrahimAmin1 made their first contribution in https://github.com/bentoml/BentoML/pull/4360
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.1.10...v1.1.11
- Python
Published by aarnphm over 2 years ago
bentoml - BentoML - v1.1.10
Released a patch that set the upper bound for cattrs<23.2, which breaks our whole serialisation process both upstream and downstream.
What's Changed
- fix: StreamingResponse compatibility issue by @xianml in https://github.com/bentoml/BentoML/pull/4248
- bentocloud doc update --data field by @MingLiangDai in https://github.com/bentoml/BentoML/pull/4272
- docs: Add repository and bento selection notes by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4280
- fix(dispatcher): unbounded overload batch_size by @aarnphm in https://github.com/bentoml/BentoML/pull/4273
- docs: update transformers example to include gpu options by @ssheng in https://github.com/bentoml/BentoML/pull/4281
- fix monitoring docs configuration.yaml typo by @KimSoungRyoul in https://github.com/bentoml/BentoML/pull/4287
- fix: runnable framework logic in transformers.py by @benfu-verses in https://github.com/bentoml/BentoML/pull/4291
- docs: Update docs on supported CUDA versions by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4288
- docs: Add docs for new transformers model import API by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4282
- fix: Disable exception in serve-grpc on Windows in development mode by @zimka in https://github.com/bentoml/BentoML/pull/4294
- fix(dependencies): lock cattrs<23.2 for now by @aarnphm in https://github.com/bentoml/BentoML/pull/4292
New Contributors
- @benfu-verses made their first contribution in https://github.com/bentoml/BentoML/pull/4291
- @zimka made their first contribution in https://github.com/bentoml/BentoML/pull/4294
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.1.9...v1.1.10
- Python
Published by aarnphm over 2 years ago
bentoml - BentoML - v1.1.9
- Import Hugging Face Transformers Model: the
bentoml.transformers.import_modelAPI imports pretrained transformers models directly from HuggingFace. Using this API allows importing Transformers models into the BentoML model store without loading the model into memory. Thebentoml.transformers.import_modelAPI takes the first argument to be the model name in BentoML store, and the second argument to be themodel_idon HuggingFace Hub.
```python import bentoml
bentomodel = bentoml.transformers.import_model("zephyr-7b-beta", "HuggingFaceH4/zephyr-7b-beta") ```
- Standardize with
nvidia-ml-py: BentoML now uses the officialnvidia-ml-pypackage instead ofpynvmlto avoid conflict with other packages. - Define Environment Variable in Configuration: Within
bentoml_configuration.yaml, values in the form of${ENV_VAR}will be expanded at runtime to the value of the corresponding environment variable, but please note that this only supports string types.
What's Changed
- docs: Update the deployment docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4260
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/4264
- feat: import model for transformers framework by @MingLiangDai in https://github.com/bentoml/BentoML/pull/4247
- build: Use official nvidia-ml-py package instead of fork by @ecederstrand in https://github.com/bentoml/BentoML/pull/4208
New Contributors
- @MingLiangDai made their first contribution in https://github.com/bentoml/BentoML/pull/4247
- @ecederstrand made their first contribution in https://github.com/bentoml/BentoML/pull/4208
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.1.7...v1.1.9
- Python
Published by ssheng over 2 years ago
bentoml - BentoML - v1.1.8
What's Changed
- docs: Add the OpenLLM Llama 2 Colab link by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4235
- docs: Add best practices doc for building and deploying Bentos by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4237
- docs: Update the bento building and deployment best practices doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4242
- docs: Add global token and token expiration in docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4243
- fix: client API by @alexparker443 in https://github.com/bentoml/BentoML/pull/4245
- docs: Update the Bentos doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4246
- docs: Update OneDiffusion Colab link by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4249
- fix: suppress abstractmethod TypeError of TritonRunnerHandle by @netoou in https://github.com/bentoml/BentoML/pull/4251
- fix: send request ID in response headers in all cases by @frostming in https://github.com/bentoml/BentoML/pull/4253
- fix(client): prepend http if necessary in wait by @sauyon in https://github.com/bentoml/BentoML/pull/4255
- fix: Bug 4252 Restore functioning benoml.ray.deployment by @jerryharrow in https://github.com/bentoml/BentoML/pull/4257
- fix(client): add http if required to sync client wait by @sauyon in https://github.com/bentoml/BentoML/pull/4258
- fix(ci): fix tests by @sauyon in https://github.com/bentoml/BentoML/pull/4259
- feat: support storing secrets with env vars in config by @frostming in https://github.com/bentoml/BentoML/pull/4254
New Contributors
- @alexparker443 made their first contribution in https://github.com/bentoml/BentoML/pull/4245
- @netoou made their first contribution in https://github.com/bentoml/BentoML/pull/4251
- @jerryharrow made their first contribution in https://github.com/bentoml/BentoML/pull/4257
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.1.7...v1.1.8
- Python
Published by ssheng over 2 years ago
bentoml - BentoML - v1.1.7
What's Changed
Update OTEL deps to 0.41b0 to address CVE for 0.39b0
General documentation client updates.
- docs: Add the SDXL deployment quickstart by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4175
- Update pytorch.rst by @piercus in https://github.com/bentoml/BentoML/pull/4176
- chore(deps): bump actions/checkout from 3 to 4 by @dependabot in https://github.com/bentoml/BentoML/pull/4177
- fix: parse tag from multiline output by @frostming in https://github.com/bentoml/BentoML/pull/4178
- docs: Update the user management docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4186
- fix(config): set default runner timeout to 15min by @sauyon in https://github.com/bentoml/BentoML/pull/4184
- docs: Add observability to the BentoCloud overview docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4187
- fix(framework): add args and kwargs to sklearn and xgboost methods by @jianshen92 in https://github.com/bentoml/BentoML/pull/4189
- docs: fix typo in bento.rst and model.rst by @seedspirit in https://github.com/bentoml/BentoML/pull/4192
- fix: Rename ASGIHTTPSender to BufferedASGISender for Ray compatibility. by @HamzaFarhan in https://github.com/bentoml/BentoML/pull/4191
- fix(client): make get_client raise instead of logging by @sauyon in https://github.com/bentoml/BentoML/pull/4181
- fix(cloud-client): delete unused field of schema by @Haivilo in https://github.com/bentoml/BentoML/pull/4196
- chore(deps): bump docker/setup-buildx-action from 2 to 3 by @dependabot in https://github.com/bentoml/BentoML/pull/4195
- chore(deps): bump docker/setup-qemu-action from 2 to 3 by @dependabot in https://github.com/bentoml/BentoML/pull/4194
- chore: clientrequesthook type fix by @sauyon in https://github.com/bentoml/BentoML/pull/4199
- docs: Add docs for the new bentoml.Server API by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4198
- docs: Add the OneDiffusion Google Colab task by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4202
- docs: Add best practices doc for cost optimization by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4200
- docs: Update the Manage Models and Bentos docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4203
- fix: do not use UDS on WSL by @frostming in https://github.com/bentoml/BentoML/pull/4204
- docs: fix typos in help messages by @smidm in https://github.com/bentoml/BentoML/pull/4206
- fix: subprocess not using same python as main process causing
bentoml.bentos.buildto crash by @nickolasrm in https://github.com/bentoml/BentoML/pull/4209 - fix: allow WSL in the condition by @frostming in https://github.com/bentoml/BentoML/pull/4210
- docs: Update manage access token docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4215
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/4216
- fix: EasyOCR integration docs mistake by @jianshen92 in https://github.com/bentoml/BentoML/pull/4214
- fix: include mounted FastAPI app's OpenAPI components by @RobbieFernandez in https://github.com/bentoml/BentoML/pull/4212
- UPDATE: model.py -> fix Model class Exepction message. by @JminJ in https://github.com/bentoml/BentoML/pull/4219
- docs: Remove private access mention by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4221
- docs: Change to sentence case by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4222
- docs: Fix dead link by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4225
- feat: support ipv6 addresses for serve by @sauyon in https://github.com/bentoml/BentoML/pull/3914
- docs: Fix all dead links in BentoML docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4229
- docs: Add the BYOC doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4223
- docs: Update the Services doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4231
- fix(client): type fixes by @sauyon in https://github.com/bentoml/BentoML/pull/4182
- fix: correct the bento size to include the size of models by @frostming in https://github.com/bentoml/BentoML/pull/4226
- fix: use httpx for usage tracking by @sauyon in https://github.com/bentoml/BentoML/pull/4228
- fix(deps): bump otel for CVE by @aarnphm in https://github.com/bentoml/BentoML/pull/4233
- feat: separate and optimize async and sync clients by @judahrand in https://github.com/bentoml/BentoML/pull/4116
New Contributors
- @piercus made their first contribution in https://github.com/bentoml/BentoML/pull/4176
- @seedspirit made their first contribution in https://github.com/bentoml/BentoML/pull/4192
- @HamzaFarhan made their first contribution in https://github.com/bentoml/BentoML/pull/4191
- @nickolasrm made their first contribution in https://github.com/bentoml/BentoML/pull/4209
- @JminJ made their first contribution in https://github.com/bentoml/BentoML/pull/4219
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.1.6...v1.1.7
- Python
Published by aarnphm over 2 years ago
bentoml - BentoML - v1.1.6
What's Changed
- fix(exception): catch exception for users' runners code by @aarnphm in https://github.com/bentoml/BentoML/pull/4150
- docs: Add the streaming docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4164
- ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in https://github.com/bentoml/BentoML/pull/4167
- fix(httpclient): take into account trailing slash in from_url by @sauyon in https://github.com/bentoml/BentoML/pull/4169
- docs: fix typo by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4173
- fix: apply env map for distributed runner workers by @bojiang in https://github.com/bentoml/BentoML/pull/4174
New Contributors
- @pre-commit-ci made their first contribution in https://github.com/bentoml/BentoML/pull/4167
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.1.5...v1.1.6
- Python
Published by ssheng over 2 years ago
bentoml - BentoML - v1.1.5
What's Changed
- fix(type): explicit init for attrs Runner by @aarnphm in https://github.com/bentoml/BentoML/pull/4140
- fix: typo in ALLOWEDCUDAVERSION_ARGS by @thomasjo in https://github.com/bentoml/BentoML/pull/4156
- chore(deps): open Starlette version, to allow latest by @alexeyshockov in https://github.com/bentoml/BentoML/pull/4100
- chore: lower bound for cloudpickle by @aarnphm in https://github.com/bentoml/BentoML/pull/4098
- docs: Add embedded runners docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4157
- fix cloud client types by @sauyon in https://github.com/bentoml/BentoML/pull/4160
- fix: use closer-integrated callbackwrapper by @sauyon in https://github.com/bentoml/BentoML/pull/4161
- chore(annotations): cleanup compat and fix ModelSignatureDict type by @aarnphm in https://github.com/bentoml/BentoML/pull/4162
- fix(pull): correct use
cloud_contextfor models pull by @aarnphm in https://github.com/bentoml/BentoML/pull/4163
New Contributors
- @thomasjo made their first contribution in https://github.com/bentoml/BentoML/pull/4156
- @alexeyshockov made their first contribution in https://github.com/bentoml/BentoML/pull/4100
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.1.4...v1.1.5
- Python
Published by ssheng over 2 years ago
bentoml - BentoML - v1.1.4
🍱 To better support LLM serving through response streaming, we are proud to introduce an experimental support of server-sent events (SSE) streaming support in this release of BentoML v1.14 and OpenLLM v0.2.27. See an example service definition for SSE streaming with Llama2.
- Added response streaming through SSE to the
bentoml.io.TextIO Descriptor type. - Added async generator support to both API Server and Runner to
yieldincremental text responses. - Added supported to ☁️ BentoCloud to natively support SSE streaming.
🦾 OpenLLM added token streaming capabilities to support streaming responses from LLMs.
Added
/v1/generate_streamendpoint for streaming responses from LLMs.bash curl -N -X 'POST' 'http://0.0.0.0:3000/v1/generate_stream' -H 'accept: application/json' -H 'Content-Type: application/json' -d '{ "prompt": "### Instruction:\n What is the definition of time (200 words essay)?\n\n### Response:", "llm_config": { "use_llama2_prompt": false, "max_new_tokens": 4096, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "use_cache": true, "temperature": 0.89, "top_k": 50, "top_p": 0.76, "typical_p": 1, "epsilon_cutoff": 0, "eta_cutoff": 0, "diversity_penalty": 0, "repetition_penalty": 1, "encoder_repetition_penalty": 1, "length_penalty": 1, "no_repeat_ngram_size": 0, "renormalize_logits": false, "remove_invalid_values": false, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "encoder_no_repeat_ngram_size": 0, "n": 1, "best_of": 1, "presence_penalty": 0.5, "frequency_penalty": 0, "use_beam_search": false, "ignore_eos": false }, "adapter_name": null }'
What's Changed
- docs: Update the models doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4145
- docs: Add more workflows to the GitHub Actions doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4146
- docs: Add text embedding example to readme by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4151
- fix: bento build cache miss by @xianml in https://github.com/bentoml/BentoML/pull/4153
- fix(buildx): parsing attestation on docker desktop by @aarnphm in https://github.com/bentoml/BentoML/pull/4155
New Contributors
- @xianml made their first contribution in https://github.com/bentoml/BentoML/pull/4153
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.1.3...v1.1.4
- Python
Published by aarnphm almost 3 years ago
bentoml - BentoML - v1.1.2
Patch releases
BentoML now provides a new diffusers integration, bentoml.diffusers_simple.
This introduces two integration for stable_diffusion and stable_diffusion_xl model.
```python import bentoml
Create a Runner for a Stable Diffusion model
runner = bentoml.diffuserssimple.stablediffusion.create_runner("CompVis/stable-diffusion-v1-4")
Create a Runner for a Stable Diffusion XL model
runnerxl = bentoml.diffuserssimple.stablediffusionxl.create_runner("stabilityai/stable-diffusion-xl-base-1.0") ```
General bug fixes and documentation improvement
What's Changed
- docs: Add the Overview and Quickstarts sections by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4088
- chore(type): makes ModelInfo mypy-compatible by @aarnphm in https://github.com/bentoml/BentoML/pull/4094
- feat(store): update annotations by @aarnphm in https://github.com/bentoml/BentoML/pull/4092
- docs: Fix some relative links by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4097
- docs: Add the Iris quickstart doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4096
- docs: Add the yolo quickstart by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4099
- docs: Code format fix by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4101
- fix: respect environment during
bentoml.bentos.buildby @aarnphm in https://github.com/bentoml/BentoML/pull/4081 - docs: replaced deprecated save to save_model in pytorch.rst by @EgShes in https://github.com/bentoml/BentoML/pull/4102
- fix: Make the install command shorter by @frostming in https://github.com/bentoml/BentoML/pull/4103
- docs: Update the BentoCloud Build doc by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4104
- docs: Add quickstart repo link and move torch import in Yolo by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4106
- docs: fix typo by @zhangwm404 in https://github.com/bentoml/BentoML/pull/4108
- docs: fix typo by @zhangwm404 in https://github.com/bentoml/BentoML/pull/4109
- fix: calculate Pandas DataFrame batch size correctly by @judahrand in https://github.com/bentoml/BentoML/pull/4110
- fix(cli): fix CLI output to BentoCloud by @Haivilo in https://github.com/bentoml/BentoML/pull/4114
- Fix sklearn example docs by @jianshen92 in https://github.com/bentoml/BentoML/pull/4121
- docs: Add the BentoCloud Deployment creation and update page property explanations by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4105
- fix: disable pyright for being too strict by @frostming in https://github.com/bentoml/BentoML/pull/4113
- refactor(cli): change prompt of cloud cli to unify Yatai and BentoCloud by @Haivilo in https://github.com/bentoml/BentoML/pull/4124
- fix(cli): change model to lower case by @Haivilo in https://github.com/bentoml/BentoML/pull/4126
- chore(ci): remove codestyle jobs by @aarnphm in https://github.com/bentoml/BentoML/pull/4125
- fix: don't pass column names twice by @judahrand in https://github.com/bentoml/BentoML/pull/4120
- feat: SSE (Experimental) by @jianshen92 in https://github.com/bentoml/BentoML/pull/4083
- docs: Restructure the get started section in BentoCloud docs by @Sherlock113 in https://github.com/bentoml/BentoML/pull/4129
- docs: change monitoring image by @Haivilo in https://github.com/bentoml/BentoML/pull/4133
- feat: Rust gRPC client by @aarnphm in https://github.com/bentoml/BentoML/pull/3368
- feature(framework): diffusers lora and textual inversion support by @larme in https://github.com/bentoml/BentoML/pull/4086
- feat(buildx): support for attestation and sbom with buildx by @aarnphm in https://github.com/bentoml/BentoML/pull/4132
New Contributors
- @EgShes made their first contribution in https://github.com/bentoml/BentoML/pull/4102
- @zhangwm404 made their first contribution in https://github.com/bentoml/BentoML/pull/4108
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.1.1...v1.1.2
- Python
Published by aarnphm almost 3 years ago
bentoml - BentoML - v1.1.1
🍱 Patched release 1.1.1
- Added more extensive cloud config option for
bentoml deploymentCLI, Thanks @Haivilo. Note thatbentoml deployment updatenow takes the name as a optional positional argument instead of the previous behaviour--name:bash bentoml deployment update DEPLOYMENT_NAMESee #4087 - Added documentation about bento release GitHub action, Thanks @frostming. See #4071
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.1.0...v1.1.1
- Python
Published by aarnphm almost 3 years ago
bentoml - BentoML - v1.1.0
🍱 We're thrilled to announce the release of BentoML v1.1.0, our first minor version update since the milestone v1.0.
- Backward Compatibility: Rest assured that this release maintains full API backward compatibility with v1.0.
- Official gRPC Support: We've transitioned gRPC support in BentoML from experimental to official status, expanding your toolkit for high-performance, low-latency services.
- Ray Integration: Ray is a popular open-source compute framework that makes it easy to scale Python workloads. BentoML integrates natively with Ray Serve to enable users to deploy Bento applications in a Ray cluster without modifying code or configuration.
- Enhanced Hugging Face Transformers and Diffusers Support: All Hugging Face Diffuser models and pipelines can be seamlessly imported and integrated into BentoML applications through the Transformers and Diffusers framework libraries.
- Enhanced Model Version Management: Enjoy greater flexibility with the improved model version management, enabling flexible configuration and synchronization of model versions with your remote model store.
🦾 We are also excited to announce the launch of OpenLLM v0.2.0 featuring the support of Llama 2 models.
- GPU and CPU Support: Running Llama is support on both GPU and CPU.
Model variations and parameter sizes: Support all model weights and parameter sizes on Hugging Face.
bash meta-llama/llama-2-70b-chat-hf meta-llama/llama-2-13b-chat-hf meta-llama/llama-2-7b-chat-hf meta-llama/llama-2-70b-hf meta-llama/llama-2-13b-hf meta-llama/llama-2-7b-hf openlm-research/open_llama_7b_v2 openlm-research/open_llama_3b_v2 openlm-research/open_llama_13b huggyllama/llama-65b huggyllama/llama-30b huggyllama/llama-13b huggyllama/llama-7bUsers can use any weights on HuggingFace (e.g.
TheBloke/Llama-2-13B-chat-GPTQ), custom weights from local path (e.g./path/to/llama-1), or fine-tuned weights as long as it adheres to LlamaModelForCausalLM.Stay tuned for Fine-tuning capabilities in OpenLLM: Fine-tuning various Llama 2 models will be added in a future release. Try the experimental script for fine-tuning Llama-2 with QLoRA under OpenLLM playground.
python -m openllm.playground.llama2_qlora --help
- Python
Published by ssheng almost 3 years ago
bentoml - BentoML - v1.0.22
🍱 BentoML v1.0.22 release has brought a list of well-anticipated updates.
- Added support for Pydantic 2 for better validate performance.
- Added support for CUDA 12 versions in builds and containerization.
Introduced service lifecycle events allowing adding custom logic
on_deployment,on_startup, andon_shutdown. States can be managed using the contextctxvariable during theon_startupandon_shutdownevents and during request serving in the API.```python @svc.ondeployment def ondeployment(): pass
@svc.onstartup def onstartup(ctx: bentoml.Context): ctx.state["objectkey"] = createobject()
@svc.onshutdown def onshutdown(ctx: bentoml.Context): cleanupstate(ctx.state["objectkey"])
@svc.api def predict(inputdata, ctx): object = ctx.state["objectkey"] pass ```
Added support for traffic control for both API Server and Runners. Timeout and maximum concurrency can now be configured through configuration.
```bash apiserver: traffic: timeout: 10 # API Server request timeout in seconds maxconcurrency: 32 # Maximum concurrency requests in the API Server
runners: iris: traffic: timeout: 10 # Runner request timeout in seconds max_concurrency: 32 # Maximum concurrency requests in the Runner ```
Improved performance of
bentoml pushperformance for large Bentos.
🚀 One more thing, the team is delighted to unveil our latest endeavor, OpenLLM. This innovative project allows you to effortless build with the state-of-the-art open source or fine-tuned Large Language Models.
Supports all variants of Flan-T5, Dolly V2, StarCoder, Falcon, StableLM, and ChatGLM out-of-box. Fully customizable with model specific arguments.
bash openllm start [falcon | flan_t5 | dolly_v2 | chatglm | stablelm | starcoder]Exposes the familiar BentoML APIs and transforms LLMs seamlessly into Runners.
bash llm_runner = openllm.Runner("dolly-v2")Builds LLM application into the Bento format that can be deployed to BentoCloud or containerized into OCI images.
bash openllm build [falcon | flan_t5 | dolly_v2 | chatglm | stablelm | starcoder]
Our dedicated team is working hard to pioneering more integrations of advanced models for our upcoming releases of OpenLLM. Stay tuned for the unfolding developments.
- Python
Published by ssheng almost 3 years ago
bentoml - BentoML - v1.0.20
🍱 BentoML v1.0.20 is released with improved usability and compatibility features.
- Production Mode by Default:
bentoml servecommand will now run with the--productionoption by default. The change is made the simulate the production behavior during development. The--reloadoption will continue to with as expected. To achieve the serving behavior previously, use--developmentinstead. Optional Dependency for OpenTelemetry Exporter: The
opentelemetry-exporter-otlp-proto-httpdependency has been moved from a required dependency to an optional one to address aprotobufdependency incompatibility issue. ⚠️ If you are currently using the Model Monitoring and Inference Data Collection feature, you must install the package with themonitor-otlp****option from this release onwards to include the necessary dependency.python pip install "bentoml[monitor-otlp]"OpenTelemetry Trace ID Configuration Option: A new configuration option has been added to return the OpenTelemetry Trace ID in the response. This feature is particularly helpful when tracing has not been initialized in the upstream caller, but the caller still wishes to log the Trace ID in case of an error.
yaml
api_server:
http:
response:
trace_id: True
- Start from a Service: Added the ability to start a server from a
bentoml.Serviceobject. This is helpful for troubleshooting a project in a development environment where no Bentos has been built yet.
```python import bentoml
# import the Service defined in /clip_api_service/service.py file
from clipapiservice.service import svc
if name == "main": # start a server: server = bentoml.HTTPServer(svc) server.start(blocking=False) client = server.get_client() client.predict(..) ```
What's Changed
- fix(dispatcher): handling empty ostat in `triggerrefresh` by @larme in https://github.com/bentoml/BentoML/pull/3796
- fix(framework): adjust diffusers device_map default behavior by @larme in https://github.com/bentoml/BentoML/pull/3779
- chore(dispatcher): cancel jobs with a for loop by @sauyon in https://github.com/bentoml/BentoML/pull/3788
- fix: correctly reraise
CancelledErrorby @sauyon in https://github.com/bentoml/BentoML/pull/3801 - use path as resource for non-OS paths by @sauyon in https://github.com/bentoml/BentoML/pull/3800
- chore(deps): bump coverage[toml] from 7.2.3 to 7.2.4 by @dependabot in https://github.com/bentoml/BentoML/pull/3803
- feat: embedded runner by @larme in https://github.com/bentoml/BentoML/pull/3735
- feat(tensorflow): support list types inputs by @enmanuelmag in https://github.com/bentoml/BentoML/pull/3807
- chore(deps): bump ruff from 0.0.263 to 0.0.264 by @dependabot in https://github.com/bentoml/BentoML/pull/3817
- feat: subprocess build by @aarnphm in https://github.com/bentoml/BentoML/pull/3814
- docs: update community slack links by @parano in https://github.com/bentoml/BentoML/pull/3824
- chore(deps): bump pyarrow from 11.0.0 to 12.0.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3820
- chore(deps): remove imageio by @aarnphm in https://github.com/bentoml/BentoML/pull/3812
- chore(deps): bump tritonclient[all] from 2.32.0 to 2.33.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3795
- ci: add Pillow to tests dependencies by @aarnphm in https://github.com/bentoml/BentoML/pull/3830
- feat(observability): support
service.nameby @aarnphm in https://github.com/bentoml/BentoML/pull/3825 - feat: optional returning trace_id in response by @aarnphm in https://github.com/bentoml/BentoML/pull/3827
- chore: 3.11 support by @PeterJCLaw in https://github.com/bentoml/BentoML/pull/3792
- fix: Eliminate the exception during shutdown by @frostming in https://github.com/bentoml/BentoML/pull/3826
- chore: expose schedulingstrategy in torunner by @bojiang in https://github.com/bentoml/BentoML/pull/3831
- feat: allow starting server with bentoml.Service instance by @parano in https://github.com/bentoml/BentoML/pull/3829
- chore(deps): bump bufbuild/buf-setup-action from 1.17.0 to 1.18.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3838
- fix: make sure to set content-type for file type by @aarnphm in https://github.com/bentoml/BentoML/pull/3837
- docs: update default docs to use env as key:value instead of list type by @aarnphm in https://github.com/bentoml/BentoML/pull/3841
- deps: move exporter-proto to optional by @aarnphm in https://github.com/bentoml/BentoML/pull/3840
- feat(server): improve server APIs by @aarnphm in https://github.com/bentoml/BentoML/pull/3834
New Contributors
- @enmanuelmag made their first contribution in https://github.com/bentoml/BentoML/pull/3807
- @PeterJCLaw made their first contribution in https://github.com/bentoml/BentoML/pull/3792
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.0.19...v1.0.20
- Python
Published by ssheng about 3 years ago
bentoml - BentoML - v1.0.19
🍱 BentoML v1.0.19 is released with enhanced GPU utilization and expanded ML framework support.
Optimized GPU resource utilization: Enabled scheduling of multiple instances of the same runner using the
workers_per_resourcescheduling strategy configuration. The following configuration allows scheduling 2 instances of the “iris” runner per GPU instance.workers_per_resourceis 1 by default.yaml runners: iris: resources: nvidia.com/gpu: 1 workers_per_resource: 2New ML framework support: We've added support for EasyOCR and Detectron2 to our growing list of supported ML frameworks.
Enhanced runner communication: Implemented PEP 574 out-of-band pickling to improve runner communication by eliminating memory copying, resulting in better performance and efficiency.
Backward compatibility for Hugging Face Transformers: Resolved compatibility issues with Hugging Face Transformers versions prior to
v4.18, ensuring a seamless experience for users with older versions.
⚙️ With the release of Kubeflow 1.7, BentoML now has native integration with Kubeflow, allowing developers to leverage BentoML's cloud-native components. Prior, developers were limited to exporting and deploying Bento as a single container. With this integration, models trained in Kubeflow can easily be packaged, containerized, and deployed to a Kubernetes cluster as microservices. This architecture enables the individual models to run in their own pods, utilizing the most optimal hardware for their respective tasks and enabling independent scaling.
💡 With each release, we consistently update our blog, documentation and examples to empower the community in harnessing the full potential of BentoML.
- Learn more scheduling strategy to get better resource utilization.
- Learn more about model monitoring and drift detection in BentoML and integration with various monitoring framework.
- Learn more about using Nvidia Triton Inference Server as a runner to improve your application’s performance and throughput.
What's Changed
- fix(env): using
python -mto run pip commands by @frostming in https://github.com/bentoml/BentoML/pull/3762 - chore(deps): bump pytest from 7.3.0 to 7.3.1 by @dependabot in https://github.com/bentoml/BentoML/pull/3766
- feat: lazy load
bentoml.serverby @aarnphm in https://github.com/bentoml/BentoML/pull/3763 - fix(client): service route prefix by @aarnphm in https://github.com/bentoml/BentoML/pull/3765
- chore: add test with many requests by @sauyon in https://github.com/bentoml/BentoML/pull/3768
- fix: using http config for grpc server by @aarnphm in https://github.com/bentoml/BentoML/pull/3771
- feat: apply pep574 out-of-band pickling to DefaultContainer by @larme in https://github.com/bentoml/BentoML/pull/3736
- fix: passing serve_cmd and passthrough kwargs by @aarnphm in https://github.com/bentoml/BentoML/pull/3764
- feat: Detectron by @aarnphm in https://github.com/bentoml/BentoML/pull/3711
- chore(dispatcher): (re-)factor out training code by @sauyon in https://github.com/bentoml/BentoML/pull/3767
- feat: EasyOCR by @aarnphm in https://github.com/bentoml/BentoML/pull/3712
- feat(build): support 3.11 by @aarnphm in https://github.com/bentoml/BentoML/pull/3774
- patch: backports module availability for transformers<4.18 by @aarnphm in https://github.com/bentoml/BentoML/pull/3775
- fix(dispatcher): set wait to 0 while training by @sauyon in https://github.com/bentoml/BentoML/pull/3664
- chore(deps): bump ruff from 0.0.261 to 0.0.262 by @dependabot in https://github.com/bentoml/BentoML/pull/3778
- feat: add
model#load_modelmethod by @parano in https://github.com/bentoml/BentoML/pull/3780 - feat: Allow spawning more than 1 worker on each resource by @frostming in https://github.com/bentoml/BentoML/pull/3776
- docs: Fix TensorFlow
save_modelparameter order by @ssheng in https://github.com/bentoml/BentoML/pull/3781 - chore(deps): bump yamllint from 1.30.0 to 1.31.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3782
- chore(deps): bump imageio from 2.27.0 to 2.28.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3783
- chore(deps): bump ruff from 0.0.262 to 0.0.263 by @dependabot in https://github.com/bentoml/BentoML/pull/3790
- fix: allow import service defined under a Python package by @parano in https://github.com/bentoml/BentoML/pull/3794
New Contributors
- @frostming made their first contribution in https://github.com/bentoml/BentoML/pull/3762
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.0.18...v1.0.19
- Python
Published by ssheng about 3 years ago
bentoml - BentoML - v1.0.18
🍱 BentoML v1.0.18 brings a new way of creating the server and client natively from Python.
Start an HTTP or gRPC server and client asynchronously with a context manager.
```python server = HTTPServer("iris_classifier:latest", production=True, port=3000)
Start the server in a separate process and connect to it using a client
with server.start() as client: res = client.classify(np.array([[4.9, 3.0, 1.4, 0.2]])) ```
Start an HTTP or gRPC server synchronously.
python server = HTTPServer("iris_classifier:latest", production=True, port=3000) server.start(blocking=True)As always, a client can be created and connected to an running server.
python client = Client.from_url("http://localhost:3000") res = client.classify(np.array([[4.9, 3.0, 1.4, 0.2]]))What's Changed
chore(deps): bump coverage[toml] from 7.2.2 to 7.2.3 by @dependabot in https://github.com/bentoml/BentoML/pull/3746
bugs: Fix an f-string bug in Tranformers framework. by @ssheng in https://github.com/bentoml/BentoML/pull/3753
chore(deps): bump pytest from 7.2.2 to 7.3.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3751
chore(deps): bump bufbuild/buf-setup-action from 1.16.0 to 1.17.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3750
fix: BufferError when pushing model to BentoCloud by @aarnphm in https://github.com/bentoml/BentoML/pull/3737
chore: remove codecov dependencies by @aarnphm in https://github.com/bentoml/BentoML/pull/3754
feat: implement new serve API by @sauyon in https://github.com/bentoml/BentoML/pull/3696
examples: Add a client example to quickstart by @ssheng in https://github.com/bentoml/BentoML/pull/3752
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.0.17...v1.0.18
- Python
Published by ssheng about 3 years ago
bentoml - BentoML - v1.0.17
🍱 We are excited to announce the release of BentoML v1.0.17, which includes support for 🤗 Hugging Face Transformers pre-trained instances. Prior to this release, only pipelines could be saved and loaded using the bentoml.transformers APIs. However, based on the community's demand to work with pre-trained models, tokenizers, preprocessors, etc., without pipelines, we have expanded our capabilities in bentoml.transformers APIs. With this release, all pre-trained instances can be saved and loaded into either built-in Transformers framework runners or custom runners. This update opens up new possibilities for users to work with pre-trained models, and we are thrilled to see what the community will create using this feature. To learn more, visit BentoML Transformers framework documentation.
Pre-trained models and instances, such as tokenizers, preprocessors, and feature extractors, can also be saved as standalone models using the
bentoml.transformers.save_modelAPI.```python import bentoml from transformers import AutoTokenizer
processor = SpeechT5Processor.frompretrained("microsoft/speecht5tts") model = SpeechT5ForTextToSpeech.frompretrained("microsoft/speecht5tts") vocoder = SpeechT5HifiGan.frompretrained("microsoft/speecht5hifigan")
bentoml.transformers.savemodel("speecht5ttsprocessor", processor) bentoml.transformers.savemodel("speecht5ttsmodel", model, signatures={"generatespeech": {"batchable": False}}) bentoml.transformers.savemodel("speecht5ttsvocoder", vocoder) ```
Pre-trained models and instances can be run either independently as Transformers framework runners or jointly in a custom runner. To use pre-trained models and instances as individual framework runners, simply get the models reference and convert them to runners using the
to_runnermethod.```python import bentoml import torch
from bentoml.io import Text, NumpyNdarray from datasets import load_dataset
proccessorrunner = bentoml.transformers.get("speecht5ttsprocessor").torunner() modelrunner = bentoml.transformers.get("speecht5ttsmodel").torunner() vocoderrunner = bentoml.transformers.get("speecht5ttsvocoder").torunner() embeddingsdataset = loaddataset("Matthijs/cmu-arctic-xvectors", split="validation") speakerembeddings = torch.tensor(embeddingsdataset[7306]["xvector"]).unsqueeze(0)
svc = bentoml.Service("text2speech", runners=[proccessorrunner, modelrunner, vocoder_runner])
@svc.api(input=Text(), output=NumpyNdarray()) def generatespeech(inp: str): inputs = proccessorrunner.run(text=inp, returntensors="pt") speech = modelrunner.generatespeech.run(inputids=inputs["inputids"], speakerembeddings=speakerembeddings, vocoder=vocoderrunner.run) return speech.numpy() ```
To use the pre-trained models and instances together in a custom runner, use the
bentoml.transformers.getAPI to get the models references and load them in a custom runner. The pretrained instances can then be used for inference in the custom runner.```python import bentoml import torch
from datasets import load_dataset
processorref = bentoml.models.get("speecht5ttsprocessor:latest") modelref = bentoml.models.get("speecht5ttsmodel:latest") vocoderref = bentoml.models.get("speecht5tts_vocoder:latest")
class SpeechT5Runnable(bentoml.Runnable):
def __init__(self): self.processor = bentoml.transformers.load_model(processor_ref) self.model = bentoml.transformers.load_model(model_ref) self.vocoder = bentoml.transformers.load_model(vocoder_ref) self.embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation") self.speaker_embeddings = torch.tensor(self.embeddings_dataset[7306]["xvector"]).unsqueeze(0) @bentoml.Runnable.method(batchable=False) def generate_speech(self, inp: str): inputs = self.processor(text=inp, return_tensors="pt") speech = self.model.generate_speech(inputs["input_ids"], self.speaker_embeddings, vocoder=self.vocoder) return speech.numpy()text2speechrunner = bentoml.Runner(SpeechT5Runnable, name="speecht5runner", models=[processorref, modelref, vocoderref]) svc = bentoml.Service("talkgpt", runners=[text2speech_runner])
@svc.api(input=bentoml.io.Text(), output=bentoml.io.NumpyNdarray()) async def generatespeech(inp: str): return await text2speechrunner.generatespeech.asyncrun(inp) ```
What's Changed
- feat(containerize): caching pip/conda installation layers by @smidm in https://github.com/bentoml/BentoML/pull/3673
- docs(batching): update docs to 503 by @sauyon in https://github.com/bentoml/BentoML/pull/3677
- chore(deps): bump ruff from 0.0.255 to 0.0.256 by @dependabot in https://github.com/bentoml/BentoML/pull/3676
- fix(type): annotate PdSeries with pandas-stubs by @aarnphm in https://github.com/bentoml/BentoML/pull/3466
- chore(dispatcher): refactor out training code by @sauyon in https://github.com/bentoml/BentoML/pull/3663
- fix: makes containerize for triton examples to all amd64 by @aarnphm in https://github.com/bentoml/BentoML/pull/3678
- chore(deps): bump coverage[toml] from 7.2.1 to 7.2.2 by @dependabot in https://github.com/bentoml/BentoML/pull/3679
- revert: "chore(dispatcher): refactor out training code (#3663)" by @sauyon in https://github.com/bentoml/BentoML/pull/3680
- doc: add more links to Bentoml/examples by @larme in https://github.com/bentoml/BentoML/pull/3631
- perf: serialization optimization by @larme in https://github.com/bentoml/BentoML/pull/3606
- examples: Kubeflow by @ssheng in https://github.com/bentoml/BentoML/pull/3656
- chore(deps): bump pytest-asyncio from 0.20.3 to 0.21.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3688
- chore(deps): bump ruff from 0.0.256 to 0.0.257 by @dependabot in https://github.com/bentoml/BentoML/pull/3689
- chore(deps): bump imageio from 2.26.0 to 2.26.1 by @dependabot in https://github.com/bentoml/BentoML/pull/3690
- chore(deps): bump yamllint from 1.29.0 to 1.30.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3694
- fix: remove duplicate dependabot check for pip by @aarnphm in https://github.com/bentoml/BentoML/pull/3691
- chore(deps): bump ruff from 0.0.257 to 0.0.258 by @dependabot in https://github.com/bentoml/BentoML/pull/3699
- docs: Update the Kubeflow example by @ssheng in https://github.com/bentoml/BentoML/pull/3703
- chore(deps): bump ruff from 0.0.258 to 0.0.259 by @dependabot in https://github.com/bentoml/BentoML/pull/3709
- docs: add link to pyfilesystem plugins by @sauyon in https://github.com/bentoml/BentoML/pull/3716
- docs: Kubeflow integration documentation by @ssheng in https://github.com/bentoml/BentoML/pull/3704
- docs: replace loadrunner() to get().torunner() by @KimSoungRyoul in https://github.com/bentoml/BentoML/pull/3715
- chore(deps): bump imageio from 2.26.1 to 2.27.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3720
- fix(readme): format markdown table by @aarnphm in https://github.com/bentoml/BentoML/pull/3722
- fix: copy files before running
setup_scriptby @aarnphm in https://github.com/bentoml/BentoML/pull/3713 - chore: remove experimental warning for
bentoml.metricsby @aarnphm in https://github.com/bentoml/BentoML/pull/3725 - ci: temporary disable coverage by @aarnphm in https://github.com/bentoml/BentoML/pull/3726
- chore(deps): bump ruff from 0.0.259 to 0.0.260 by @dependabot in https://github.com/bentoml/BentoML/pull/3734
- chore(deps): bump tritonclient[all] from 2.31.0 to 2.32.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3730
- fix(type):
bentoml.container.buildshould accept multipleimage_tagby @pmayd in https://github.com/bentoml/BentoML/pull/3719 - chore(deps): bump bufbuild/buf-setup-action from 1.15.1 to 1.16.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3738
- feat: add query params to request context by @sauyon in https://github.com/bentoml/BentoML/pull/3717
- chore(dispatcher): use attr class instead of a tuple by @sauyon in https://github.com/bentoml/BentoML/pull/3731
- fix: Make it so the configured maxbatchsize is respected when batching inference requests together by @RShang97 in https://github.com/bentoml/BentoML/pull/3741
- feat(transformers): pretrained protocol support by @aarnphm in https://github.com/bentoml/BentoML/pull/3684
- fix(tests): broken CI by @aarnphm in https://github.com/bentoml/BentoML/pull/3742
- chore(deps): bump ruff from 0.0.260 to 0.0.261 by @dependabot in https://github.com/bentoml/BentoML/pull/3744
- docs: Transformers documentation on pre-trained instances support by @ssheng in https://github.com/bentoml/BentoML/pull/3745
New Contributors
- @smidm made their first contribution in https://github.com/bentoml/BentoML/pull/3673
- @pmayd made their first contribution in https://github.com/bentoml/BentoML/pull/3719
- @RShang97 made their first contribution in https://github.com/bentoml/BentoML/pull/3741
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.0.16...v1.0.17
- Python
Published by ssheng about 3 years ago
bentoml - BentoML - v1.0.16
🍱 BentoML v1.0.16 release is here featuring the introduction of the bentoml.triton framework. With this integration, BentoML now supports running NVIDIA Triton Inference Server as a Runner. See Triton Inference Server documentation to learn more!
Triton Inference Server can be configured as a Runner in BentoML with its model repository and CLI arguments specified as parameters.
```python import bentoml
tritonrunner = bentoml.triton.Runner( "tritonrunner", modelrepository="s3://bucket/path/to/modelrepository", cliargs=["--load-model=torchscripyolov5s", "--model-control-mode=explicit"], ) ```
Models served by the Triton Inference Server Runner can be called as a method on the runner handle both synchronously and asynchronously.
python @svc.api( input=bentoml.io.Image.from_sample("./data/0.png"), output=bentoml.io.NumpyNdarray() ) async def bentoml_torchscript_mnist_infer(im: Image) -> NDArray[t.Any]: arr = np.array(im) / 255.0 arr = np.expand_dims(arr, (0, 1)).astype("float32") InferResult = await triton_runner.torchscript_mnist.async_run(arr) return InferResult.as_numpy("OUTPUT__0")Build bentos and containerize images with Triton Runners by specifying
nvcr.io/nvidia/tritonserverbase image inbentofile.yaml.```yaml service: service:svc include:
- /model_repository
- /data/*.png
- /*.py exclude:
- /pycache
- /venv
- /train.py
- /build_bento.py
- /containerize_bento.py
python:
packages:
- bentoml[triton] docker: base_image: nvcr.io/nvidia/tritonserver:22.12-py3 ```
💡 If you are an existing Triton user, the integration provides simpler ways to add custom logics in Python, deploy distributed multi-model inference graph, unify model management across different ML frameworks and workflows, and standardize model packaging format with versioning and collaboration features. If you are an existing BentoML user, the integration improves the runner efficiency and throughput under high load thanks to Triton’s efficient C++ runtime.
What's Changed
- fix(container): podman virtual machine healthcheck (#3575) by @timc in https://github.com/bentoml/BentoML/pull/3576
- chore(aiohttp): remove deprecated verify_ssl to ssl by @aarnphm in https://github.com/bentoml/BentoML/pull/3574
- feat(triton): support HTTP client by @aarnphm in https://github.com/bentoml/BentoML/pull/3502
- fix(grpc): handle backward protocol version by @aarnphm in https://github.com/bentoml/BentoML/pull/3332
- chore(deps): bump ruff from 0.0.246 to 0.0.247 by @dependabot in https://github.com/bentoml/BentoML/pull/3579
- chore(test): using container API for testing by @aarnphm in https://github.com/bentoml/BentoML/pull/3582
- fix(serve-cli): Make sure to use BENTOML_CONFIG value by @aarnphm in https://github.com/bentoml/BentoML/pull/3597
- docs: Update documentation with an examples link by @ssheng in https://github.com/bentoml/BentoML/pull/3599
- chore: lock starlette version by @sauyon in https://github.com/bentoml/BentoML/pull/3600
- feature(diffusers): support
enable_attention_slicingby @larme in https://github.com/bentoml/BentoML/pull/3598 - chore(cli): figlet to show on CLI only by @aarnphm in https://github.com/bentoml/BentoML/pull/3603
- chore(cli): using default background as color by @aarnphm in https://github.com/bentoml/BentoML/pull/3608
- feat: Flax by @aarnphm in https://github.com/bentoml/BentoML/pull/3123
- feat(gRPC): client implementation by @aarnphm in https://github.com/bentoml/BentoML/pull/3280
- fix: invalid option dtype=True for pd.read_csv by @parano in https://github.com/bentoml/BentoML/pull/3601
- chore(deps): bump coverage[toml] from 7.1.0 to 7.2.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3616
- chore(deps): bump ruff from 0.0.247 to 0.0.252 by @dependabot in https://github.com/bentoml/BentoML/pull/3617
- docs: containerisation API by @aarnphm in https://github.com/bentoml/BentoML/pull/3518
- chore(deps): bump coverage[toml] from 7.2.0 to 7.2.1 by @dependabot in https://github.com/bentoml/BentoML/pull/3621
- chore(deps): bump imageio from 2.25.1 to 2.26.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3620
- fix(docs): missing space bug causes table not to render by @aarnphm in https://github.com/bentoml/BentoML/pull/3622
- chore(deps): bump ruff from 0.0.252 to 0.0.253 by @dependabot in https://github.com/bentoml/BentoML/pull/3624
- feat: enable cork for non-batched workloads by @sauyon in https://github.com/bentoml/BentoML/pull/3602
- docs: Fix typo in concepts/service by @FelixSchuSi in https://github.com/bentoml/BentoML/pull/3627
- chore(deps): bump tritonclient[all] from 2.30.0 to 2.31.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3628
- fix(docs): broken inline docstring by @aarnphm in https://github.com/bentoml/BentoML/pull/3538
- fix: use a semaphore to limit runner connections by @sauyon in https://github.com/bentoml/BentoML/pull/3607
- fix: make inference_api handle None type by @aarnphm in https://github.com/bentoml/BentoML/pull/3611
- fix: make sure not to override user set values for from_sample by @aarnphm in https://github.com/bentoml/BentoML/pull/3610
- docs: add exceptions API section by @aarnphm in https://github.com/bentoml/BentoML/pull/3609
- revert(pyproject): add back pytest plugins by @aarnphm in https://github.com/bentoml/BentoML/pull/3633
- fix(configuration): CORS docs,
allow_originsandallow_headersby @larme in https://github.com/bentoml/BentoML/pull/3643 - chore(deps): bump ruff from 0.0.253 to 0.0.254 by @dependabot in https://github.com/bentoml/BentoML/pull/3641
- chore(deps): bump pytest from 7.2.1 to 7.2.2 by @dependabot in https://github.com/bentoml/BentoML/pull/3642
- chore: http client healthcheck by @denyszhak in https://github.com/bentoml/BentoML/pull/3636
- docs: typo in configuration.rst by @davkime in https://github.com/bentoml/BentoML/pull/3644
- docs: correct links to configuration source code by @davkime in https://github.com/bentoml/BentoML/pull/3645
- example: add fraud detection and benchmark examples by @parano in https://github.com/bentoml/BentoML/pull/3647
- fix(containerize): remove autoconfig for buildctl by @aarnphm in https://github.com/bentoml/BentoML/pull/3484
- feat: name in bentofile.yaml by @aarnphm in https://github.com/bentoml/BentoML/pull/3604
- chore: ensure all labels are dict[str,str] by @aarnphm in https://github.com/bentoml/BentoML/pull/3605
- fix(triton): enable runtime options by @aarnphm in https://github.com/bentoml/BentoML/pull/3649
- docs: Triton Inference Server by @aarnphm in https://github.com/bentoml/BentoML/pull/3519
- example: Triton Inference Server by @aarnphm in https://github.com/bentoml/BentoML/pull/3471
- chore(deps): bump pytest from 7.2.1 to 7.2.2 in /requirements by @dependabot in https://github.com/bentoml/BentoML/pull/3639
- chore(deps): bump bufbuild/buf-setup-action from 1.14.0 to 1.15.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3638
- fix: some missing logics for triton examples by @aarnphm in https://github.com/bentoml/BentoML/pull/3650
- fix: use async implementation by @characat0 in https://github.com/bentoml/BentoML/pull/3654
- feat: add ray deploy support by @parano in https://github.com/bentoml/BentoML/pull/3632
- chore(deps): bump pytest-xdist[psutil] from 3.2.0 to 3.2.1 by @dependabot in https://github.com/bentoml/BentoML/pull/3659
- chore(deps): bump bufbuild/buf-setup-action from 1.15.0 to 1.15.1 by @dependabot in https://github.com/bentoml/BentoML/pull/3655
- fix: update scheme logic using ssl.enabled by @aarnphm in https://github.com/bentoml/BentoML/pull/3660
- feat:
from_sampledocstring by @aarnphm in https://github.com/bentoml/BentoML/pull/3318 - fix(ci): locking starlette for container tests by @aarnphm in https://github.com/bentoml/BentoML/pull/3666
- chore: better exception for numpy by @sauyon in https://github.com/bentoml/BentoML/pull/3665
- feat: make file io descriptor allow any mime type by default by @sauyon in https://github.com/bentoml/BentoML/pull/3626
- fix(docs): broken link by @aarnphm in https://github.com/bentoml/BentoML/pull/3537
- chore(stubs): remove unused by @aarnphm in https://github.com/bentoml/BentoML/pull/3612
- docs: Update Triton documentation and examples by @ssheng in https://github.com/bentoml/BentoML/pull/3668
- chore(deps): bump ruff from 0.0.254 to 0.0.255 by @dependabot in https://github.com/bentoml/BentoML/pull/3671
- docs: Update integration docs by @ssheng in https://github.com/bentoml/BentoML/pull/3672
New Contributors
- @FelixSchuSi made their first contribution in https://github.com/bentoml/BentoML/pull/3627
- @denyszhak made their first contribution in https://github.com/bentoml/BentoML/pull/3636
- @davkime made their first contribution in https://github.com/bentoml/BentoML/pull/3644
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.0.15...v1.0.16
- Python
Published by ssheng about 3 years ago
bentoml - BentoML - v1.0.15
🍱 BentoML v1.0.15 release is here featuring the introduction of the bentoml.diffusers framework.
- Learn more about the capabilities of the
bentoml.diffusersframework in the Creating Stable Diffusion 2.0 Service With BentoML And Diffusers blog and BentoML Diffusers example project. Import a diffusion model with the
bentoml.diffusers.import_modelAPI.```python import bentoml
bentoml.diffusers.import_model( "sd2", "stabilityai/stable-diffusion-2", ) ```
Create a
text2imgservice using a Stable Diffusion 2.0 model runner with the familiarto_runnerAPI from thebentoml.diffuserframework.```python import torch from diffusers import StableDiffusionPipeline
import bentoml from bentoml.io import Image, JSON, Multipart
bentomodel = bentoml.diffusers.get("sd2:latest") stablediffusionrunner = bentomodel.to_runner()
svc = bentoml.Service("stablediffusionv2", runners=[stablediffusionrunner])
@svc.api(input=JSON(), output=Image()) def txt2img(inputdata): images, _ = stablediffusionrunner.run(**inputdata) return images[0] ```
🍱 Fixed a incompatibility change introduced in starlette==0.25.0 result in the type MultiPartMessage not being found in starlette.formparsers.
ImportError: cannot import name 'MultiPartMessage' from 'starlette.formparsers' (/opt/miniconda3/envs/bentoml/lib/python3.10/site-packages/starlette/formparsers.py)
What's Changed
- chore(deps): bump pytest-xdist[psutil] from 3.1.0 to 3.2.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3536
- fix: include dockerfile_template to Bento for containerize by @aarnphm in https://github.com/bentoml/BentoML/pull/3501
- chore: add missing logger and fix types by @aarnphm in https://github.com/bentoml/BentoML/pull/3453
- chore(rtd): disable epub and pdf as format by @aarnphm in https://github.com/bentoml/BentoML/pull/3544
- feat(torchscript): support
_extra_filesby @aarnphm in https://github.com/bentoml/BentoML/pull/3480 - refactor(ci): make sure to run types on py,pyi files by @aarnphm in https://github.com/bentoml/BentoML/pull/3545
- fix(server): deprecate client and cache get_client by @aarnphm in https://github.com/bentoml/BentoML/pull/3547
- chore(serve): update options for triton_options by @aarnphm in https://github.com/bentoml/BentoML/pull/3503
- tools(linter): Ruff by @aarnphm in https://github.com/bentoml/BentoML/pull/3539
- chore(deps): bump ruff from 0.0.243 to 0.0.244 by @dependabot in https://github.com/bentoml/BentoML/pull/3548
- chore(type): remove cattr type ignore by @aarnphm in https://github.com/bentoml/BentoML/pull/3550
- chore: bumping otlp deps to 1.15 by @aarnphm in https://github.com/bentoml/BentoML/pull/3351
- docs: Add an example index by @ssheng in https://github.com/bentoml/BentoML/pull/3551
- revert: "chore: bumping otlp deps to 1.15" by @bojiang in https://github.com/bentoml/BentoML/pull/3553
- chore(deps): bump bufbuild/buf-setup-action from 1.13.1 to 1.14.0 by @dependabot in https://github.com/bentoml/BentoML/pull/3554
- chore(deps): bump ruff from 0.0.244 to 0.0.246 by @dependabot in https://github.com/bentoml/BentoML/pull/3559
- chore(deps): bump imageio from 2.25.0 to 2.25.1 by @dependabot in https://github.com/bentoml/BentoML/pull/3557
- chore: update README.md by @timliubentoml in https://github.com/bentoml/BentoML/pull/3565
- feat(containerization): support 11.7 by @aarnphm in https://github.com/bentoml/BentoML/pull/3567
- chore: remove deprecation warning when building bentos by @CheeksTheGeek in https://github.com/bentoml/BentoML/pull/3566
- feature(framework): diffusers by @larme in https://github.com/bentoml/BentoML/pull/3534
- fix: update formparser for new starlette by @sauyon in https://github.com/bentoml/BentoML/pull/3569
New Contributors
- @CheeksTheGeek made their first contribution in https://github.com/bentoml/BentoML/pull/3566
Full Changelog: https://github.com/bentoml/BentoML/compare/v1.0.14...v1.0.15
- Python
Published by ssheng over 3 years ago
bentoml - BentoML - v1.0.14
🍱 Fixed the backward incompatibility introduced in starlette version 0.24.0. Upgrade BentoML to v1.0.14 if you encounter the error related to content_type like below.
Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/bentoml/_internal/server/service_app.py", line 305, in api_func
input_data = await api.input.from_http_request(request)
File "/usr/local/lib/python3.8/dist-packages/bentoml/_internal/io_descriptors/multipart.py", line 208, in from_http_request
reqs = await populate_multipart_requests(request)
File "/usr/local/lib/python3.8/dist-packages/bentoml/_internal/utils/formparser.py", line 188, in populate_multipart_requests
form = await multipart_parser.parse()
File "/usr/local/lib/python3.8/dist-packages/bentoml/_internal/utils/formparser.py", line 158, in parse
multipart_file = UploadFile(
TypeError: __init__() got an unexpected keyword argument 'content_type'
- Python
Published by ssheng over 3 years ago