Recent Releases of embed
embed - 0.0.77
What's Changed
- Update colpali engine to latest version by @wirthual in https://github.com/michaelfeil/infinity/pull/563
- Add ColQwen25 to IMAGECOL_MODELS by @yasyf in https://github.com/michaelfeil/infinity/pull/568
- add deps by @michaelfeil in https://github.com/michaelfeil/infinity/pull/570
- [Docs] Correct outdated mention of OpenAIEmbeddingInput by @HollowMan6 in https://github.com/michaelfeil/infinity/pull/587
- Caching huggingface models in GH actions by @wirthual in https://github.com/michaelfeil/infinity/pull/602
- Fix client generation pipeline by @wirthual in https://github.com/michaelfeil/infinity/pull/603
- Fix broken link in README by @davidpaquin in https://github.com/michaelfeil/infinity/pull/622
- adding hf-xet by @michaelfeil in https://github.com/michaelfeil/infinity/pull/632
- fix linting in select_model.py by @wirthual in https://github.com/michaelfeil/infinity/pull/633
- New torch version (2.8) New flash attnention, remove hf_transfer by @michaelfeil in https://github.com/michaelfeil/infinity/pull/636
New Contributors
- @yasyf made their first contribution in https://github.com/michaelfeil/infinity/pull/568
- @HollowMan6 made their first contribution in https://github.com/michaelfeil/infinity/pull/587
- @davidpaquin made their first contribution in https://github.com/michaelfeil/infinity/pull/622
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.76...0.0.77
- Python
Published by michaelfeil 6 months ago
embed - 0.0.76
- torch=2.6.0 update - 5-10% faster attention on hopper -> previously 2.4.1 -> does no longer work with torch.compile + bettertransformers. We recommend disabling torch.compile for this model class.
- flash-attn included in docker image for nvidia.
What's Changed
- bump client version by @wirthual in https://github.com/michaelfeil/infinity/pull/522
- add new st version by @michaelfeil in https://github.com/michaelfeil/infinity/pull/523
- Version check step by @wirthual in https://github.com/michaelfeil/infinity/pull/524
- README: add example for using local model wtth docker container by @wirthual in https://github.com/michaelfeil/infinity/pull/528
- add vision client template by @wirthual in https://github.com/michaelfeil/infinity/pull/526
- bump to 2.6 torch by @michaelfeil in https://github.com/michaelfeil/infinity/pull/556
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.75...0.0.76
- Python
Published by michaelfeil 12 months ago
embed - 0.0.75
What's Changed
- add better bettertransformers support by @michaelfeil in https://github.com/michaelfeil/infinity/pull/509
- Update verbose parameter when initializing ModelWorker by @aRyBernAlTEglOTRO in https://github.com/michaelfeil/infinity/pull/516 THANKS!
- 0.0.75 release by @michaelfeil in https://github.com/michaelfeil/infinity/pull/520 -> DEFAULTS to
v2command in the CLI
New Contributors
- @aRyBernAlTEglOTRO made their first contribution in https://github.com/michaelfeil/infinity/pull/516 THANKS !
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.74...0.0.75
- Python
Published by michaelfeil about 1 year ago
embed - 0.0.74
What's Changed
- move cli to extra file, macOS tests add documentation by @michaelfeil in https://github.com/michaelfeil/infinity/pull/501
- Modernbert support, adding latest huggingface from source by @michaelfeil in https://github.com/michaelfeil/infinity/pull/508
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.73...0.0.74
- Python
Published by michaelfeil about 1 year ago
embed - 0.0.73
What's Changed
- Support for matryoshka embeddings by @wirthual in https://github.com/michaelfeil/infinity/pull/490
- Adding optimum option for PredictEngine by @wwymak in https://github.com/michaelfeil/infinity/pull/492
- new-release by @michaelfeil in https://github.com/michaelfeil/infinity/pull/494
New Contributors
- @wwymak made their first contribution in https://github.com/michaelfeil/infinity/pull/492
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.72...0.0.73
- Python
Published by michaelfeil about 1 year ago
embed - 0.0.72
What's Changed
- Adds neuron support by @michaelfeil in https://github.com/michaelfeil/infinity/pull/486
- Fix python classification example by @molntamas in https://github.com/michaelfeil/infinity/pull/487
- add max size by @michaelfeil in https://github.com/michaelfeil/infinity/pull/489
New Contributors
- @molntamas made their first contribution in https://github.com/michaelfeil/infinity/pull/487
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.71...0.0.72
- Python
Published by michaelfeil about 1 year ago
embed - 0.0.71
What's Changed
- update transformers package by @wirthual in https://github.com/michaelfeil/infinity/pull/471
- Fix: openvino by @michaelfeil in https://github.com/michaelfeil/infinity/pull/475
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.70...0.0.71
- Python
Published by michaelfeil about 1 year ago
embed - 0.0.70
What's Changed
- Queue refactor by @michaelfeil in https://github.com/michaelfeil/infinity/pull/462
- Update README.md by @LetsssGo55 in https://github.com/michaelfeil/infinity/pull/425
- Update functional.py by @YadlaMani in https://github.com/michaelfeil/infinity/pull/419
- Revert "Update functional.py" by @michaelfeil in https://github.com/michaelfeil/infinity/pull/466
- Optimum amd support by @michaelfeil in https://github.com/michaelfeil/infinity/pull/464
- DROP PYDANTIC 1.x by @michaelfeil in https://github.com/michaelfeil/infinity/pull/465
- update release pipeline by @michaelfeil in https://github.com/michaelfeil/infinity/pull/469
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.69...0.0.70
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.69
What's Changed
- Readme and Doc update by @michaelfeil in https://github.com/michaelfeil/infinity/pull/459
- add openvino, trt by @michaelfeil in https://github.com/michaelfeil/infinity/pull/460
- add dtype-based loading by @michaelfeil in https://github.com/michaelfeil/infinity/pull/461
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.68...0.0.69
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.68
What's Changed
- add benchmark for clip model by @wirthual in https://github.com/michaelfeil/infinity/pull/438
- Vision fix for non-clip models by @michaelfeil in https://github.com/michaelfeil/infinity/pull/439
- Add PR template (With changes) by @fadkeabhi in https://github.com/michaelfeil/infinity/pull/441
- Fixed Broken License Link in README by @niranjan-kurhade in https://github.com/michaelfeil/infinity/pull/446
- change embedding response object to list for openai compatibility by @wirthual in https://github.com/michaelfeil/infinity/pull/444
- README: Add KubeAI under integrations by @samos123 in https://github.com/michaelfeil/infinity/pull/453
- Model: Device-id and data-parallel inference in CLI and Torch by @michaelfeil in https://github.com/michaelfeil/infinity/pull/452
- Colbert by @michaelfeil in https://github.com/michaelfeil/infinity/pull/456
New Contributors
- @niranjan-kurhade made their first contribution in https://github.com/michaelfeil/infinity/pull/446
- @samos123 made their first contribution in https://github.com/michaelfeil/infinity/pull/453
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.67...0.0.68
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.66
What's Changed
- Add better start messages & telemetry documenation by @michaelfeil in https://github.com/michaelfeil/infinity/pull/429
- poetry unlock by @michaelfeil in https://github.com/michaelfeil/infinity/pull/430
- end-2-end faster tests by @michaelfeil in https://github.com/michaelfeil/infinity/pull/431
- Docker update trt onnx by @michaelfeil in https://github.com/michaelfeil/infinity/pull/432
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.65...0.0.66
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.64
What's Changed
- Tests: Add base64 test for audio endpoint by @wirthual in https://github.com/michaelfeil/infinity/pull/414
- Add PR template by @fadkeabhi in https://github.com/michaelfeil/infinity/pull/417
- add regex validation by @michaelfeil in https://github.com/michaelfeil/infinity/pull/420
- improve pytest download tooling by @michaelfeil in https://github.com/michaelfeil/infinity/pull/421
- Colipali - ready for review. by @michaelfeil in https://github.com/michaelfeil/infinity/pull/423
New Contributors
- @fadkeabhi made their first contribution in https://github.com/michaelfeil/infinity/pull/417
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.63...0.0.64
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.63
What's Changed
- improve typing to 3.9 standards by @michaelfeil in https://github.com/michaelfeil/infinity/pull/409
- add posthog logging by @michaelfeil in https://github.com/michaelfeil/infinity/pull/410
How to disable logging:
```
across docker, cli
export DONOTTRACK=1 ```
- add bfloat16 as dtype
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.62...0.0.63
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.62
What's Changed: Breaking change - rerank endpoint returns sorted results
- add top_k parameter to rerank endpoint (#396) by @michaelfeil in https://github.com/michaelfeil/infinity/pull/404
- docs: update README.md by @eltociear in https://github.com/michaelfeil/infinity/pull/405
- fix topk tests by @michaelfeil in https://github.com/michaelfeil/infinity/pull/406
- update client by @michaelfeil in https://github.com/michaelfeil/infinity/pull/407
New Contributors
- @eltociear made their first contribution in https://github.com/michaelfeil/infinity/pull/405
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.61...0.0.62
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.60
What's Changed
- Embed openai broad multimodal compat by @michaelfeil in https://github.com/michaelfeil/infinity/pull/395 -> MultiModal inference in /embeddings
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.59...0.0.60
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.59
What's Changed
- add client packages by @michaelfeil in https://github.com/michaelfeil/infinity/pull/382
- WIP: End to End test for vision and audio by @wirthual in https://github.com/michaelfeil/infinity/pull/386
- Follow up PR for Audio End to End testing by @wirthual in https://github.com/michaelfeil/infinity/pull/390
- Feature: Add Support for Data URI by @davleop in https://github.com/michaelfeil/infinity/pull/385
- Allow enabling rerankers raw_scores by @rawsh in https://github.com/michaelfeil/infinity/pull/393
New Contributors
- @davleop made their first contribution in https://github.com/michaelfeil/infinity/pull/385
- @rawsh made their first contribution in https://github.com/michaelfeil/infinity/pull/393
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.58...0.0.59
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.58
What's Changed
- async requests enabled by @michaelfeil in https://github.com/michaelfeil/infinity/pull/376
- Update README. Extract audio related code into own utils by @wirthual in https://github.com/michaelfeil/infinity/pull/380
- Audio: OpenAI API by @michaelfeil in https://github.com/michaelfeil/infinity/pull/377
- add libsound for docker arm build by @michaelfeil in https://github.com/michaelfeil/infinity/pull/381
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.57...0.0.58
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.57
What's Changed
- format with ruff by @michaelfeil in https://github.com/michaelfeil/infinity/pull/365
- Update README.md by @shell-nlp in https://github.com/michaelfeil/infinity/pull/368
- WIP: Add CLAP support by @wirthual in https://github.com/michaelfeil/infinity/pull/364
- add weakref to sync engine by @michaelfeil in https://github.com/michaelfeil/infinity/pull/373
- add verification check by @michaelfeil in https://github.com/michaelfeil/infinity/pull/374
New Contributors
- @shell-nlp made their first contribution in https://github.com/michaelfeil/infinity/pull/368
- @wirthual made their first contribution in https://github.com/michaelfeil/infinity/pull/364
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.56...0.0.57
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.56
What's Changed
- Solution to #258 [CLIP][Server/Engine] Send images to engine / accept PIL images by @Gavinfornever in https://github.com/michaelfeil/infinity/pull/353
New Contributors
- @Gavinfornever made their first contribution in https://github.com/michaelfeil/infinity/pull/353
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.55...0.0.56
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.55
What's Changed
- add vast example to infra by @aowen14 in https://github.com/michaelfeil/infinity/pull/343
- Update README.md with logos by @michaelfeil in https://github.com/michaelfeil/infinity/pull/346
- fixing link by @aowen14 in https://github.com/michaelfeil/infinity/pull/347
- add disk_cleanup action by @kartik-ganesh in https://github.com/michaelfeil/infinity/pull/348
- Update README.md by @michaelfeil in https://github.com/michaelfeil/infinity/pull/351
- base64 encoding option for embeddings by @michaelfeil in https://github.com/michaelfeil/infinity/pull/350
New Contributors
- @aowen14 made their first contribution in https://github.com/michaelfeil/infinity/pull/343
- @kartik-ganesh made their first contribution in https://github.com/michaelfeil/infinity/pull/348
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.54...0.0.55
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.53
What's Changed
- docs update by @michaelfeil in https://github.com/michaelfeil/infinity/pull/315
- weakref-sync by @michaelfeil in https://github.com/michaelfeil/infinity/pull/318
- Update pyproject.toml by @michaelfeil in https://github.com/michaelfeil/infinity/pull/322
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.52...0.0.53
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.52
What's Changed
- [Client] add initial client code by @michaelfeil in https://github.com/michaelfeil/infinity/pull/292
- Add a prefix to the openapi document by @wangm23456 in https://github.com/michaelfeil/infinity/pull/296
- update embed package by @michaelfeil in https://github.com/michaelfeil/infinity/pull/302
- Benchmark update with
embedby @michaelfeil in https://github.com/michaelfeil/infinity/pull/311 - optimization onnx with optimum by @michaelfeil in https://github.com/michaelfeil/infinity/pull/310
- lock poetry by @michaelfeil in https://github.com/michaelfeil/infinity/pull/312
- Add flash_attn support (#306) by @michaelfeil in https://github.com/michaelfeil/infinity/pull/313
New Contributors
- @wangm23456 made their first contribution in https://github.com/michaelfeil/infinity/pull/296
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.51...0.0.52
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.50
What's Changed
- Fix auth when no token is passed + add auth to /models by @chiragjn in https://github.com/michaelfeil/infinity/pull/287
- Update tests for #287 by @chiragjn in https://github.com/michaelfeil/infinity/pull/288
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.49...0.0.50
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.49
What's Changed
- Update skypilot-infinity.yaml by @michaelfeil in https://github.com/michaelfeil/infinity/pull/284
- Bump simpleinference by @michaelfeil in https://github.com/michaelfeil/infinity/pull/285
- api changes sync async by @michaelfeil in https://github.com/michaelfeil/infinity/pull/286
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.48...0.0.49
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.47
What's Changed
- add nightly and pypi pull by @michaelfeil in https://github.com/michaelfeil/infinity/pull/274
- refactor modal webserver by @charlesfrye in https://github.com/michaelfeil/infinity/pull/275
- add sync array by @michaelfeil in https://github.com/michaelfeil/infinity/pull/277
- fix: vision unpin by @michaelfeil in https://github.com/michaelfeil/infinity/pull/279
- simplify-ci by @michaelfeil in https://github.com/michaelfeil/infinity/pull/278
- add easyinference by @michaelfeil in https://github.com/michaelfeil/infinity/pull/280
New Contributors
- @charlesfrye made their first contribution in https://github.com/michaelfeil/infinity/pull/275
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.46...0.0.47
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.46
What's Changed
- add infra folder by @michaelfeil in https://github.com/michaelfeil/infinity/pull/272
- add CI/CD for infra by @michaelfeil in https://github.com/michaelfeil/infinity/pull/273
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.45...0.0.46
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.43
What's Changed
- impove bettertransformer interface by @michaelfeil in https://github.com/michaelfeil/infinity/pull/260
- Add support to pass
root_pathto FastAPI app by @chiragjn in https://github.com/michaelfeil/infinity/pull/261 - Update on docs and poetry by @michaelfeil in https://github.com/michaelfeil/infinity/pull/265
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.42...0.0.43
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.41
What's Changed
- fix pytest, rename reranker model by @michaelfeil in https://github.com/michaelfeil/infinity/pull/248
- Clip embeddings parallel by @michaelfeil in https://github.com/michaelfeil/infinity/pull/251
- clip - server follow up by @michaelfeil in https://github.com/michaelfeil/infinity/pull/249
- Transformers 4.41 bump by @michaelfeil in https://github.com/michaelfeil/infinity/pull/257
PUBLIC API CHANGE in python (internal modules no longer exposed, exposing multi-model API)
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.40...0.0.41
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.38
What's Changed
- update poetry lock to latest by @michaelfeil in https://github.com/michaelfeil/infinity/pull/234
- Add auth and classify endpoint to openai server by @Rololi in https://github.com/michaelfeil/infinity/pull/237
- ENV-Manager update by @michaelfeil in https://github.com/michaelfeil/infinity/pull/238
New Contributors
- @Rololi made their first contribution in https://github.com/michaelfeil/infinity/pull/237
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.37...0.0.38
- Python
Published by michaelfeil over 1 year ago
embed - 0.0.37
What's Changed
- bump sentence-transformers to 3.0 by @michaelfeil in https://github.com/michaelfeil/infinity/pull/232
- Add einops as extra dependency by @chiragjn in https://github.com/michaelfeil/infinity/pull/233
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.36...0.0.37
- Python
Published by michaelfeil almost 2 years ago
embed - 0.0.34
What's Changed
- Add option to enable permissive CORS headers to allow api access from… by @kir-gadjello in https://github.com/michaelfeil/infinity/pull/214
- add v2 to CLI by @michaelfeil in https://github.com/michaelfeil/infinity/pull/227
- Add revision and trustremotecode to from_pretrained calls by @chiragjn in https://github.com/michaelfeil/infinity/pull/224
New Contributors
- @kir-gadjello made their first contribution in https://github.com/michaelfeil/infinity/pull/214
- @chiragjn made their first contribution in https://github.com/michaelfeil/infinity/pull/224
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.33...0.0.34
- Python
Published by michaelfeil almost 2 years ago
embed - 0.0.33
What's Changed
- fix-orjson by @michaelfeil in https://github.com/michaelfeil/infinity/pull/201
- Add
EngineArrayMulti-Model [1/3] by @michaelfeil in https://github.com/michaelfeil/infinity/pull/200 - Openapi tests by @michaelfeil in https://github.com/michaelfeil/infinity/pull/199
- refactor
BatchHandlerintoModelWorkerby @michaelfeil in https://github.com/michaelfeil/infinity/pull/202 - Add fp32 as runtime dtype by @michaelfeil in https://github.com/michaelfeil/infinity/pull/211
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.32...0.0.33
- Python
Published by michaelfeil almost 2 years ago
embed - 0.0.32
What's Changed
You can now run a model with a alias. This will help you communicating with the API.
bash
infinity_emb --served-model-name "your_nickname"
You can now use preload models. This acts as a "run download and load into ram" test. Upon execution, all files are cached, which will speedup consecutive loads. For additonal speedups, use --no-model-warmup to skip model warmup after loading.
bash
infinity_emb --preload-only --model--name-or-path BAAI/bge-large-en-v1.5
PR's * feat: add servedmodelname argument for the infinityserver by @bufferoverflow in https://github.com/michaelfeil/infinity/pull/180 * FIX: import crossencoder without torch installed and git push of creds by @michaelfeil in https://github.com/michaelfeil/infinity/pull/181 * update default modelname to be unified name across routes by @michaelfeil in https://github.com/michaelfeil/infinity/pull/179 * python39 type hints by @michaelfeil in https://github.com/michaelfeil/infinity/pull/182 * pydantic cli / args validation by @michaelfeil in https://github.com/michaelfeil/infinity/pull/183 * update defered moving to cpu & type hints improvement by @michaelfeil in https://github.com/michaelfeil/infinity/pull/187 * Update README.md - add Contributors by @michaelfeil in https://github.com/michaelfeil/infinity/pull/189 * update infinity offline solution by @michaelfeil in https://github.com/michaelfeil/infinity/pull/195 * update offline-mode: deployment docs v2 by @michaelfeil in https://github.com/michaelfeil/infinity/pull/196
New Contributors
- @bufferoverflow made their first contribution in https://github.com/michaelfeil/infinity/pull/180 Thanks!
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.31...0.0.32
- Python
Published by michaelfeil almost 2 years ago
embed - 0.0.31
What's Changed
- Create ISSUE_TEMPLATE by @michaelfeil in https://github.com/michaelfeil/infinity/pull/168
- bump sentence transformers to v.2.6.0 by @michaelfeil in https://github.com/michaelfeil/infinity/pull/169
- Embedding quant by @michaelfeil in https://github.com/michaelfeil/infinity/pull/170
- refactor
ENUM..TypeHintinto a function by @michaelfeil in https://github.com/michaelfeil/infinity/pull/172 - refactored more imports by @michaelfeil in https://github.com/michaelfeil/infinity/pull/171
- redirect to
/docsand optional imports by @michaelfeil in https://github.com/michaelfeil/infinity/pull/175 - update typing by @michaelfeil in https://github.com/michaelfeil/infinity/pull/176
- update lock by @michaelfeil in https://github.com/michaelfeil/infinity/pull/177
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.30...0.0.31
- Python
Published by michaelfeil almost 2 years ago
embed - 0.0.30
What's Changed
- remove fastembed by @michaelfeil in https://github.com/michaelfeil/infinity/pull/141
- Sentence transformers bump to 2.5.0 by @michaelfeil in https://github.com/michaelfeil/infinity/pull/142
- Revert "Sentence transformers bump to 2.5.0" by @michaelfeil in https://github.com/michaelfeil/infinity/pull/143
- Update README.md by @michaelfeil in https://github.com/michaelfeil/infinity/pull/145
- update poetry lock - sentence-transformers 2.5.0 by @michaelfeil in https://github.com/michaelfeil/infinity/pull/144
- Support for Inferentia2 (draft) by @michaelfeil in https://github.com/michaelfeil/infinity/pull/118
- Add bettertransformer to cli by @michaelfeil in https://github.com/michaelfeil/infinity/pull/152
- Fp8 support by @michaelfeil in https://github.com/michaelfeil/infinity/pull/153
- Some docstring and typing fixes by @lckr in https://github.com/michaelfeil/infinity/pull/156
- add async tokenization to reranker in torch by @michaelfeil in https://github.com/michaelfeil/infinity/pull/154
- Update README.md by @sherwin684 in https://github.com/michaelfeil/infinity/pull/167
New Contributors
- @lckr made their first contribution in https://github.com/michaelfeil/infinity/pull/156
- @sherwin684 made their first contribution in https://github.com/michaelfeil/infinity/pull/167
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.29...0.0.30
- Python
Published by michaelfeil almost 2 years ago
embed - 0.0.29
What's Changed
- OpenAI models compatability and update docs and by @michaelfeil in https://github.com/michaelfeil/infinity/pull/140
This will be the last release with fastembed - fastembed and optimum provide similar capabilities. Please use optimum going forward.
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.28...0.0.29
- Python
Published by michaelfeil almost 2 years ago
embed - 0.0.28
What's Changed
- add macos ci by @michaelfeil in https://github.com/michaelfeil/infinity/pull/133
- Quantization: int8 by @michaelfeil in https://github.com/michaelfeil/infinity/pull/134
- add docs via mkdocs by @michaelfeil in https://github.com/michaelfeil/infinity/pull/137
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.27...0.0.28
- Python
Published by michaelfeil almost 2 years ago
embed - 0.0.27
What's Changed
- BREAKING: EngineArgs by @michaelfeil in https://github.com/michaelfeil/infinity/pull/124
- new stable interface. batch-size=32 as default. using michaelfeil/bge-small as default model. You can overwrite the pooling method now.
- multiple os ci and python 3.12 support by @michaelfeil in https://github.com/michaelfeil/infinity/pull/131
- add michaelfeil/bge-small as default model by @michaelfeil in https://github.com/michaelfeil/infinity/pull/135
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.26...0.0.27
- Python
Published by michaelfeil almost 2 years ago
embed - 0.0.26
What's Changed
- hf_transfer is automatically used by @michaelfeil in https://github.com/michaelfeil/infinity/pull/112
- add revision to onnx by @michaelfeil in https://github.com/michaelfeil/infinity/pull/109
- bump sentence-transformers to 2.4.0 by @michaelfeil in https://github.com/michaelfeil/infinity/pull/113
- Adds benchmarking by @michaelfeil in https://github.com/michaelfeil/infinity/pull/110
- ONNX/Optimum now works on windows by @michaelfeil in https://github.com/michaelfeil/infinity/pull/117
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.25...0.0.26
- Python
Published by michaelfeil almost 2 years ago
embed - 0.0.25
What's Changed
- add engine args similar to vllm by @michaelfeil in https://github.com/michaelfeil/infinity/pull/102
- ct2 bump by @michaelfeil in https://github.com/michaelfeil/infinity/pull/103
- Deps free by @michaelfeil in https://github.com/michaelfeil/infinity/pull/104
- fix: cli start by @michaelfeil in https://github.com/michaelfeil/infinity/pull/105
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.24...0.0.25
- Python
Published by michaelfeil about 2 years ago
embed - 0.0.24
What's Changed
- Update README.md contribution guidelines by @michaelfeil in https://github.com/michaelfeil/infinity/pull/91
- Update tensorrt, onnxruntime, cuda base by @michaelfeil in https://github.com/michaelfeil/infinity/pull/93
- Update dependencies by @NirantK in https://github.com/michaelfeil/infinity/pull/96
- Torch dynamic shapes by @michaelfeil in https://github.com/michaelfeil/infinity/pull/97
- update poetry version + cache in ci by @michaelfeil in https://github.com/michaelfeil/infinity/pull/99
- pydantic upgrade by @michaelfeil in https://github.com/michaelfeil/infinity/pull/100
- pydantic-v1-backwards-fixes by @michaelfeil in https://github.com/michaelfeil/infinity/pull/101
New Contributors
- @NirantK made their first contribution in https://github.com/michaelfeil/infinity/pull/96
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.23...0.0.24
- Python
Published by michaelfeil about 2 years ago
embed - 0.0.23
What's Changed
- support hf_transfer by @michaelfeil in https://github.com/michaelfeil/infinity/pull/81
- update dstack support by @deep-diver in https://github.com/michaelfeil/infinity/pull/79
- Update Dockerfile to python 3.11 + CI fix by @michaelfeil in https://github.com/michaelfeil/infinity/pull/83
- adding revision by @michaelfeil in https://github.com/michaelfeil/infinity/pull/84
- starting to deprecated fastembed and ctranslate2 by @michaelfeil in https://github.com/michaelfeil/infinity/pull/86
New Contributors
- @deep-diver made their first contribution in https://github.com/michaelfeil/infinity/pull/79 Thanks @deep-diver
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.22...0.0.23
- Python
Published by michaelfeil about 2 years ago
embed - 0.0.21
What's Changed
- improvements optimum by @michaelfeil in https://github.com/michaelfeil/infinity/pull/74
- bump sentence-transformers to 2.3.0 by @michaelfeil in https://github.com/michaelfeil/infinity/pull/76
- update dockerfile and tensorrt by @michaelfeil in https://github.com/michaelfeil/infinity/pull/75
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.20...0.0.21
- Python
Published by michaelfeil about 2 years ago
embed - 0.0.19 - yanked
What's Changed
- update optimum_utils by @michaelfeil in https://github.com/michaelfeil/infinity/pull/72
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.18...0.0.19
- Python
Published by michaelfeil about 2 years ago
embed - 0.0.17
What's Changed
Breaking: Switched to Cuda 12.1 and torch 2.1.2
- Add rerank/predict endpoint in the API by @michaelfeil in https://github.com/michaelfeil/infinity/pull/50
- update dockerfile (Cuda 12.1 and torch 2.1.2) and tests by @michaelfeil in https://github.com/michaelfeil/infinity/pull/54
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.16...0.0.17
- Python
Published by michaelfeil about 2 years ago
embed - 0.0.16
What's Changed
- fixing delayed warmup by @michaelfeil in https://github.com/michaelfeil/infinity/pull/53
- expose
capabilitiesby @michaelfeil in https://github.com/michaelfeil/infinity/pull/53
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.15...0.0.16
- Python
Published by michaelfeil about 2 years ago
embed - 0.0.13
What's Changed
- update-ci-and-readme by @michaelfeil in https://github.com/michaelfeil/infinity/pull/48
- fix-fp16 by @michaelfeil in https://github.com/michaelfeil/infinity/pull/49
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.12...0.0.13
- Python
Published by michaelfeil about 2 years ago
embed - 0.0.12
What's Changed
- add classification pipeline by @michaelfeil in https://github.com/michaelfeil/infinity/pull/44 -> See update in Readme.md
- make fp16 default for CUDA by @michaelfeil in https://github.com/michaelfeil/infinity/pull/47
- add bettertransformer by @michaelfeil in https://github.com/michaelfeil/infinity/pull/47
Breaking:
- make fp16 default for CUDA by @michaelfeil in https://github.com/michaelfeil/infinity/pull/47 -> This may lower your precision for a 2x speedup.
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.11...0.0.12
- Python
Published by michaelfeil about 2 years ago
embed - 0.0.11
What's Changed
- Refactoring of API. by @michaelfeil in https://github.com/michaelfeil/infinity/pull/43
- initial support for ReRanker models by @michaelfeil in https://github.com/michaelfeil/infinity/pull/43
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.10...0.0.11
- Python
Published by michaelfeil about 2 years ago
embed - 0.0.9
What's Changed
- Update README.md by @BrianPulfer in https://github.com/michaelfeil/infinity/pull/37
- Update README.md by @BrianPulfer in https://github.com/michaelfeil/infinity/pull/38
- add the device feature by @michaelfeil in https://github.com/michaelfeil/infinity/pull/39
New Contributors
- @BrianPulfer made their first contribution in https://github.com/michaelfeil/infinity/pull/37 also first contributor to this repo - thanks!
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.8...0.0.9
- Python
Published by michaelfeil about 2 years ago
embed - 0.0.7
What's Changed
- Docker: Cuda11.8, make dependencies optional by @michaelfeil in https://github.com/michaelfeil/infinity/pull/33
- Breaking changes: New install groups
pip install infinity-emb[server,logging,onnx-gpu-runtime] - add onnx-gpu by @michaelfeil in https://github.com/michaelfeil/infinity/pull/26
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.6...0.0.7
- Python
Published by michaelfeil over 2 years ago
embed - 0.0.5
What's Changed
- Docker image multi by @michaelfeil in https://github.com/michaelfeil/infinity/pull/24
- patch missing event -> 200ms to 7ms inference at Batch size 1
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.4...0.0.5
- Python
Published by michaelfeil over 2 years ago
embed - 0.0.4
What's Changed
PRs: * Fastembed v2 by @michaelfeil in https://github.com/michaelfeil/infinity/pull/21 :
Issues: Closes https://github.com/michaelfeil/infinity/issues/5 ONNX Support via https://github.com/qdrant/fastembed/ Closes https://github.com/michaelfeil/infinity/issues/22 making pytorch and optional dependency
tl,dr
* fastembed as backend besides ct2 or torch
* v1/models returns "backend"
* makes torch an optional dependency
* calculates "min" sleep time dynamically on startup _> slightly optimized.
* default model is now "BAAI/bge-small-en-v1.5"
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.3...0.0.4
- Python
Published by michaelfeil over 2 years ago
embed - 0.0.3
What's Changed
- add Flash-Attention+ optimum-BetterTransformers by @michaelfeil in https://github.com/michaelfeil/infinity/pull/20
- Improve real-time / sleep strategy, async await for queues and result futures - reducing latency a bit by @michaelfeil in https://github.com/michaelfeil/infinity/pull/12
- add better FIFO queueing strategy - your requests now have a upper bound how long they queue by @michaelfeil in https://github.com/michaelfeil/infinity/pull/19
Docs: * Docs: Update README.md by @michaelfeil in https://github.com/michaelfeil/infinity/pull/8 * Update description. Update pyproject.toml by @michaelfeil in https://github.com/michaelfeil/infinity/pull/9 * Refactor model dir by @michaelfeil in https://github.com/michaelfeil/infinity/pull/10 * Update README.md by @michaelfeil in https://github.com/michaelfeil/infinity/pull/14 * Update README.md by @michaelfeil in https://github.com/michaelfeil/infinity/pull/15
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.2rc0...0.0.3
- Python
Published by michaelfeil over 2 years ago
embed - 0.0.2
What's Changed
- Docs: Update README.md by @michaelfeil in https://github.com/michaelfeil/infinity/pull/8
- Update description. Update pyproject.toml by @michaelfeil in https://github.com/michaelfeil/infinity/pull/9
- Refactor model dir by @michaelfeil in https://github.com/michaelfeil/infinity/pull/10
- Improve real-time / sleep strategy, async await for queues and result futures by @michaelfeil in https://github.com/michaelfeil/infinity/pull/12
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.1...0.0.2rc0
- Python
Published by michaelfeil over 2 years ago
embed - 0.0.1-dev3
What's Changed
- startup msg, log handling, import by @michaelfeil in https://github.com/michaelfeil/infinity/pull/4
- update CI to release pypi by @michaelfeil in https://github.com/michaelfeil/infinity/pull/7
Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.1-dev2...0.0.1-dev3
- Python
Published by michaelfeil over 2 years ago
embed - 0.0.1-dev2 - Speedups
adds new dependency (orjson) for faster response serialization - 300% uses torch.inference_mode() and delayed moving to CPU - 10% adds uvicorn[standard] - slightly faster 2-5%? Updates readme
https://github.com/michaelfeil/infinity/pull/2
- Python
Published by michaelfeil over 2 years ago
embed - 0.0.1-dev1
This is a release for testing the CI of Infinity.
- Python
Published by michaelfeil over 2 years ago