autonomi-ai/nos
⚡️ A fast and flexible PyTorch inference server that runs locally, on any cloud or AI HW.
18 Releases
Latest: 2y ago
v0.3.00.3.0Latest
📋 What's Changed
- Revert "Enable cli test (#529)" by @outtanames in https://github.com/autonomi-ai/nos/pull/541
- Add device name as profile column by @outtanames in https://github.com/autonomi-ai/nos/pull/539
- Fix code in docs example by @jimburtoft in https://github.com/autonomi-ai/nos/pull/544
- Support single-container gRPC serving + HTTP proxy by @spillai in https://github.com/autonomi-ai/nos/pull/546
- Cleanup client-side integrations and tests by @spillai in https://github.com/autonomi-ai/nos/pull/548
- Add machine-to-machine API authentication example by @spillai in https://github.com/autonomi-ai/nos/pull/549
- Move base images to python 3.10 by @spillai in https://github.com/autonomi-ai/nos/pull/550
✨ New Contributors
- @jimburtoft made their first contribution in https://github.com/autonomi-ai/nos/pull/544
- Full Changelog: https://github.com/autonomi-ai/nos/compare/v0.2.0...0.3.0
v0.2.0
📦 Key PRs
- Migrate to `pydantic>=2.5`, `torch==2.1.1`, `ray[default]>=2.9` by @spillai in https://github.com/autonomi-ai/nos/pull/534
- New `inf2` runtime support with `nos serve up` by @spillai in https://github.com/autonomi-ai/nos/pull/535
📋 What's Changed
- [blog] Serving custom LLMs with SkyPilot blog post by @spillai in https://github.com/autonomi-ai/nos/pull/530
- Update blog post with new README links by @spillai in https://github.com/autonomi-ai/nos/pull/532
- Minor edit to bold text in blog post by @spillai in https://github.com/autonomi-ai/nos/pull/533
- Update profiling records without reseting catalog by @outtanames in https://github.com/autonomi-ai/nos/pull/519
- Update upload file to convert absolute path of given file. by @jiexiong2016 in https://github.com/autonomi-ai/nos/pull/524
- Enable cli test by @jiexiong2016 in https://github.com/autonomi-ai/nos/pull/529
- Profiling documentation by @outtanames in https://github.com/autonomi-ai/nos/pull/536
- New `inf2` embeddings service example by @spillai in https://github.com/autonomi-ai/nos/pull/537
- + 3 more
✨ New Contributors
- @jiexiong2016 made their first contribution in https://github.com/autonomi-ai/nos/pull/524
- Full Changelog: https://github.com/autonomi-ai/nos/compare/v0.1.5...v0.2.0
v0.1.5
📋 What's Changed
- Add a tutorial for serving animatediff by @outtanames in https://github.com/autonomi-ai/nos/pull/508
- Remove `py311-cu118` and `py38-cu121` by @spillai in https://github.com/autonomi-ai/nos/pull/514
- Fixes to profiling flow, table populates from json catalog now by @outtanames in https://github.com/autonomi-ai/nos/pull/515
- Improve network isolation for `serve up` by @spillai in https://github.com/autonomi-ai/nos/pull/516
- Support model configs w/o `model_cls` for model init on server start by @spillai in https://github.com/autonomi-ai/nos/pull/517
- Updated examples with newer API and simpler SkyPilot integration by @spillai in https://github.com/autonomi-ai/nos/pull/520
- Support unnormalized model ids in HTTP service + Skypilot deployment docs by @spillai in https://github.com/autonomi-ai/nos/pull/521
- [blog] NOS tutorials blog post by @spillai in https://github.com/autonomi-ai/nos/pull/522
- + 5 more
v0.1.4
📋 What's Changed
- Fix floating point memory specification in ModelSpec by @spillai in https://github.com/autonomi-ai/nos/pull/498
- Swap SDK for CLI as default way to start the nos server by @outtanames in https://github.com/autonomi-ai/nos/pull/499
- [blog] First blog post entry with assets by @spillai in https://github.com/autonomi-ai/nos/pull/500
- Update README and blog post for release by @spillai in https://github.com/autonomi-ai/nos/pull/503
- Add latest tag for all python versions by @outtanames in https://github.com/autonomi-ai/nos/pull/502
- [doc] Improved serve CLI documentation with serve YAML spec by @spillai in https://github.com/autonomi-ai/nos/pull/507
- New tutorial examples for serving custom models and custom methods by @spillai in https://github.com/autonomi-ai/nos/pull/509
- [tutorial] Add streaming chat tutorial by @spillai in https://github.com/autonomi-ai/nos/pull/510
- + 5 more
v0.1.3
📋 What's Changed
- Support async gRPC handling with scaled-replicas by @spillai in https://github.com/autonomi-ai/nos/pull/494
- Custom model scaling support for deployments. by @spillai in https://github.com/autonomi-ai/nos/pull/495
- Set `NOS_HOME` from cli by @outtanames in https://github.com/autonomi-ai/nos/pull/489
- Support for custom model resource limits and init args/kwargs by @spillai in https://github.com/autonomi-ai/nos/pull/492
- Various dev-ex improvements (runtime, logging etc) by @spillai in https://github.com/autonomi-ai/nos/pull/497
- Full Changelog: https://github.com/autonomi-ai/nos/compare/0.1.2...v0.1.3
0.1.2
📋 What's Changed
- Fix for `nos.profile` import on client by @spillai in https://github.com/autonomi-ai/nos/pull/484
- Update roadmap by @outtanames in https://github.com/autonomi-ai/nos/pull/485
- Full Changelog: https://github.com/autonomi-ai/nos/compare/0.1.1...0.1.2
0.1.1
📋 What's Changed
- Fix CLIP inference in main intro notebook by @outtanames in https://github.com/autonomi-ai/nos/pull/467
- Model profiler with ModelResource catalog for offline memory profiling by @spillai in https://github.com/autonomi-ai/nos/pull/468
- Support model streaming responses with new `Stream` gRPC service by @spillai in https://github.com/autonomi-ai/nos/pull/469
- Add troubleshooting instructions for macos grpcio import error until w… by @outtanames in https://github.com/autonomi-ai/nos/pull/471
- OpenAI compatible chat completions API `/v1/chat/completions` by @spillai in https://github.com/autonomi-ai/nos/pull/472
- Updates to skypilot docs with serve.yaml configuration by @spillai in https://github.com/autonomi-ai/nos/pull/473
- Update landing page and overview by @outtanames in https://github.com/autonomi-ai/nos/pull/481
- Updates to README with improved formatting. by @spillai in https://github.com/autonomi-ai/nos/pull/482
- + 2 more
0.1.0rc3
📋 What's Changed
- Add agi pack to cu118 flow as well by @outtanames in https://github.com/autonomi-ai/nos/pull/457
- Updated README / docs for public release by @spillai in https://github.com/autonomi-ai/nos/pull/456
- create-pypi-release-loose -> create-pypi-release by @outtanames in https://github.com/autonomi-ai/nos/pull/455
- Support `env_file` for `docker-compose` rendering by @spillai in https://github.com/autonomi-ai/nos/pull/458
- Support file-uploads with new HTTP endpoint by @spillai in https://github.com/autonomi-ai/nos/pull/459
- Updates to HTTP service to handle urls by @spillai in https://github.com/autonomi-ai/nos/pull/460
- Fix production FastAPI configuration by @spillai in https://github.com/autonomi-ai/nos/pull/461
- Various infra updates by @spillai in https://github.com/autonomi-ai/nos/pull/463
- + 3 more
0.1.0
📋 What's Changed
- Version bump - `0.0.10` release by @spillai in https://github.com/autonomi-ai/nos/pull/336
- Migrate PyPI package to `torch-nos` by @spillai in https://github.com/autonomi-ai/nos/pull/338
- Sweep all stable diffusion models during testing by @outtanames in https://github.com/autonomi-ai/nos/pull/334
- Publish test docker image as a github action by @outtanames in https://github.com/autonomi-ai/nos/pull/339
- Followup to #339 push docker images on release after running CI by @outtanames in https://github.com/autonomi-ai/nos/pull/340
- Test pre-release push to test PyPi by @outtanames in https://github.com/autonomi-ai/nos/pull/344
- Build pypi package before push by @outtanames in https://github.com/autonomi-ai/nos/pull/345
- NOS compiler integration with `nos-internal` by @spillai in https://github.com/autonomi-ai/nos/pull/341
- + 68 more
0.1.0rc2
📋 What's Changed
- Update CNAME for docs to https://docs.nos.run by @spillai in https://github.com/autonomi-ai/nos/pull/428
- Improved whisper transcription implementation with increased batch size by @spillai in https://github.com/autonomi-ai/nos/pull/430
- Update skypilot docs, move discord bot to GCP by @outtanames in https://github.com/autonomi-ai/nos/pull/425
- Refactor release->test->deploy flow by @outtanames in https://github.com/autonomi-ai/nos/pull/429
- Support custom models through model catalogs by @spillai in https://github.com/autonomi-ai/nos/pull/434
- Remove unused cli docs by @outtanames in https://github.com/autonomi-ai/nos/pull/436
- Move release flow to a larger runner by @outtanames in https://github.com/autonomi-ai/nos/pull/437
- New `nos serve` CLI for local serving of custom models by @spillai in https://github.com/autonomi-ai/nos/pull/438
- + 11 more
0.1.0rc1
📋 What's Changed
- Scaffolding for nos (`pyproject.toml`, `Makefile`, `pre-commit`) by @spillai in https://github.com/autonomi-ai/nos/pull/2
- Added test data to `tests/test_data` #9 by @spillai in https://github.com/autonomi-ai/nos/pull/12
- Adding Github Actions CI scaffolding #11 by @spillai in https://github.com/autonomi-ai/nos/pull/13
- Moved to mamba forge for cached builds by @spillai in https://github.com/autonomi-ai/nos/pull/15
- Added pypi project `autonomi-nos` with new makefile target by @spillai in https://github.com/autonomi-ai/nos/pull/16
- New NOS CLI entrypoint for downloading, optimizing models by @spillai in https://github.com/autonomi-ai/nos/pull/18
- Added new base dockerfile and makefile targets for py39 and trt by @spillai in https://github.com/autonomi-ai/nos/pull/19
- Updated README with badges and key features by @spillai in https://github.com/autonomi-ai/nos/pull/23
- + 192 more
✨ New Contributors
- @spillai made their first contribution in https://github.com/autonomi-ai/nos/pull/2
- @outtanames made their first contribution in https://github.com/autonomi-ai/nos/pull/31
- Full Changelog: https://github.com/autonomi-ai/nos/commits/0.1.0rc1
0.0.10
📋 What's Changed
- Add arch diagram to arch overview by @outtanames in https://github.com/autonomi-ai/nos/pull/296
- Discord bot for image generation by @outtanames in https://github.com/autonomi-ai/nos/pull/298
- New mmdetection interface with custom weights support by @spillai in https://github.com/autonomi-ai/nos/pull/309
- New model spec metadata format with runtime and model resource information by @spillai in https://github.com/autonomi-ai/nos/pull/268
- Updates to various docs for 0.0.10 release. by @spillai in https://github.com/autonomi-ai/nos/pull/310
- New super-resolution models based on LDM and Swin2SR by @spillai in https://github.com/autonomi-ai/nos/pull/311
- SDv2 Dreambooth LoRA fine-tuning API by @spillai in https://github.com/autonomi-ai/nos/pull/312
- Discord bot with NOS fine-tuning API by @spillai in https://github.com/autonomi-ai/nos/pull/314
- + 9 more
0.0.9
📋 What's Changed
- Updates to API docs, and mkdocs config by @spillai in https://github.com/autonomi-ai/nos/pull/280
- Hotfix for MacOS shared memory transport by @spillai in https://github.com/autonomi-ai/nos/pull/282
- 0.0.9 docs updates v2 by @spillai in https://github.com/autonomi-ai/nos/pull/283
- Add docs assets for 0.0.9 release by @spillai in https://github.com/autonomi-ai/nos/pull/284
- Enable multi-processing for ray workers with `OMP_NUM_THREADS>1` by @spillai in https://github.com/autonomi-ai/nos/pull/291
- Full Changelog: https://github.com/autonomi-ai/nos/compare/0.0.8...0.0.9
0.0.8
📋 What's Changed
- Enable Memray tracking by @outtanames in https://github.com/autonomi-ai/nos/pull/229
- More granular/useful client exception types by @outtanames in https://github.com/autonomi-ai/nos/pull/245
- Exclude example notebooks from pre-commit json formatting by @outtanames in https://github.com/autonomi-ai/nos/pull/254
- Re-register SAM by @outtanames in https://github.com/autonomi-ai/nos/pull/246
- Update pixeltable integration test by @outtanames in https://github.com/autonomi-ai/nos/pull/253
- Update readme to use new server launch setup by @outtanames in https://github.com/autonomi-ai/nos/pull/251
- Reduce nos.init() startup time if container is already running by @spillai in https://github.com/autonomi-ai/nos/pull/264
- CI integrations for nos and pixeltable by @spillai in https://github.com/autonomi-ai/nos/pull/263
- + 12 more
0.0.7
📋 What's Changed
- Update `grpcio-tools>=1.51.3` by @spillai in https://github.com/autonomi-ai/nos/pull/216
- Link nvidia docker instructions in quickstart by @outtanames in https://github.com/autonomi-ai/nos/pull/222
- Add noop grpc call with image input for benchmarking by @outtanames in https://github.com/autonomi-ai/nos/pull/221
- NOS profiler with notebook report by @spillai in https://github.com/autonomi-ai/nos/pull/219
- Pixeltable integration tests with no-op/yolox benchmarks by @spillai in https://github.com/autonomi-ai/nos/pull/228
- Improved `nos.init(logging_level=...)` with verbose debug logs by @spillai in https://github.com/autonomi-ai/nos/pull/230
- `0.0.7a2` release by @spillai in https://github.com/autonomi-ai/nos/pull/231
- Shared memory transport for gRPC by @spillai in https://github.com/autonomi-ai/nos/pull/224
- + 4 more
0.0.6
📋 What's Changed
- Makefile target for creating tags by @spillai in https://github.com/autonomi-ai/nos/pull/169
- Update pyproject.toml to exclude build, experimental etc. by @outtanames in https://github.com/autonomi-ai/nos/pull/170
- Set resource limits for nos container to avoid cached raylets by @spillai in https://github.com/autonomi-ai/nos/pull/174
- Refactor stable diffusion with more models and ControlNet guides by @spillai in https://github.com/autonomi-ai/nos/pull/173
- New makefile targets for benchmark tests (CPU/GPU) w/ docker variants by @spillai in https://github.com/autonomi-ai/nos/pull/176
- Improved docker CLI with simplified `nos docker stop` and `nos docker logs` by @spillai in https://github.com/autonomi-ai/nos/pull/178
- Torch FX TensorRT Conversion for YOLOX by @outtanames in https://github.com/autonomi-ai/nos/pull/177
- OpenCV-based video writer by @spillai in https://github.com/autonomi-ai/nos/pull/180
- + 14 more
0.0.5
📋 What's Changed
- Simplify server-side task dispatch without switch-case by @spillai in https://github.com/autonomi-ai/nos/pull/145
- Add segmentation service with SAM by @outtanames in https://github.com/autonomi-ai/nos/pull/126
- Fully functional runtime environment for mmdet models with tests by @spillai in https://github.com/autonomi-ai/nos/pull/149
- ModelSpec serialization `to_proto` bugfix by @spillai in https://github.com/autonomi-ai/nos/pull/151
- [benchmark] Fix benchmark tests for `0.0.5a0` by @spillai in https://github.com/autonomi-ai/nos/pull/153
- Segmentation test/fixes by @outtanames in https://github.com/autonomi-ai/nos/pull/154
- Basic opencv-based video reader for I/O by @spillai in https://github.com/autonomi-ai/nos/pull/152
- Refactored `InferenceServiceImpl` with new `ModelManager` by @spillai in https://github.com/autonomi-ai/nos/pull/155
- + 8 more
0.0.4
📋 What's Changed
- Updated client-side requirements with full testing (`client`, `e2e`, … by @spillai in https://github.com/autonomi-ai/nos/pull/107
- Client-side `WaitForServer()` and `IsHealthy()` by @spillai in https://github.com/autonomi-ai/nos/pull/108
- [docs] Public mkdocs site for client API by @spillai in https://github.com/autonomi-ai/nos/pull/109
- Add CLI tests for txt2vec (CPU), txt2img (GPU), img2bbox (GPU) by @outtanames in https://github.com/autonomi-ai/nos/pull/114
- Give CPU tests a non-parametrized name to see if it shows up in gatin… by @outtanames in https://github.com/autonomi-ai/nos/pull/122
- Rename cpu tests to allow it to be used for gating tests by @outtanames in https://github.com/autonomi-ai/nos/pull/123
- [ci] Fix name indentation for CI by @spillai in https://github.com/autonomi-ai/nos/pull/127
- Refactored prediction API with `ModelSpec` and `TensorSpec` signatures by @spillai in https://github.com/autonomi-ai/nos/pull/125
- + 6 more
