v1.4.7

What's Changed

• docs(saml): add sso saml doc by @ssheng in #5292
• docs: Add some diagrams for get started section by @Sherlock113 in #5285
• fix: do not start dependency if it's from a URL or deployment by @frostming in #5293
• feat: support pack_git_packages and fix add group for alpine by @frostming in #5295
• fix: initialize async http client with async method by @frostming in #5296
• feat: support --name option for bentoml build and bentoml code by @frostming in #5297

Full Changelog: v1.4.6...v1.4.7

v1.4.6

What's Changed

• docs: Add org token doc by @Sherlock113 in #5277
• docs: remove openllm from examples overview by @ssheng in #5278
• fix: format substitution by @byronclark in #5279
• fix: add missing .route of __endpoint by @reobroqn in #5281
• fix: non-standard ssh git url by @frostming in #5282
• docs: Update adaptive batching doc by @Sherlock113 in #5283
• docs: Add BentoOCR to example list by @Sherlock113 in #5284
• docs: Update private repo notes by @Sherlock113 in #5262
• fix: replace namespace import to python_multipart by @yxtay in #5280
• docs: Fix format by @Sherlock113 in #5287
• chore: better visibility by @bojiang in #5288
• fix: on load bento for dependent services by @frostming in #5286
• fix: visibility by @bojiang in #5289
• fix: wrong error context by @frostming in #5291

New Contributors

• @byronclark made their first contribution in #5279
• @reobroqn made their first contribution in #5281

Full Changelog: v1.4.5...v1.4.6

v1.4.5

What's Changed

• fix: loading service issue in worker by @frostming in #5276

Full Changelog: v1.4.4...v1.4.5

v1.4.4

What's Changed

• feat: update readme by @ssheng in #5259
• docs: Add update command to cloud deployment doc by @Sherlock113 in #5260
• fix: fallback to v1 if pack git packages is set by @frostming in #5261
• build: Smaller docker images by @jeffmarshall in #5264
• feat(serve): add --env and inject service-defined envs to serving environment by @aarnphm in #5263
• docs(tasks): update async tasks docs by @ssheng in #5266
• feat(client): add task apis to client methods by @frostming in #5265
• feat: default min replicas is None by @yetone in #5268
• tests: banning pickle requests by @frostming in #5269
• feat: Fail fast when running inside container by @frostming in #5270
• docs(byoc): update aws byoc role template link by @ssheng in #5272
• docs: Update langgraph example by @Sherlock113 in #5273
• fix(supervisor): quit the arbiter correctly by @frostming in #5274
• fix: preserve global options in requirements.txt by @frostming in #5275

New Contributors

• @jeffmarshall made their first contribution in #5264

Full Changelog: v1.4.3...v1.4.4

v1.4.3

What's Changed

• docs: Update examples to use new APIs by @Sherlock113 in #5252
• Add alt text to all images in documentation by @devin-ai-integration in #5253
• ci: pre-commit autoupdate [skip ci] by @pre-commit-ci in #5254
• docs: update deprecated links by @aarnphm in #5256
• docs: Add root input usage by @Sherlock113 in #5257
• fix: reformat the code by @frostming in #5258
• fix: forbid requests with pickle encoding at the entry service

Full Changelog: v1.4.2...v1.4.3

v1.4.2

What's Changed

• Fix RunPod unhashable model error by converting svc.models to hashable ids by @rivaon in #5244
• fix(io): OpenAPI schema for multipart form request body by @frostming in #5249
• fix: drop uv as a hard dependency by @frostming in #5238
• docs: Update examples to use new HF API by @Sherlock113 in #5242
• refactor: drop deepmerge dependency by @frostming in #5250
• refactor: unify logic of loading service by @frostming in #5232
• fix: collect requirements from image spec for codespaces by @frostming in #5251

New Contributors

• @rivaon made their first contribution in #5244

Full Changelog: v1.4.1...v1.4.2

v1.4.1

What's Changed

• docs: use diff for runtime image by @parano in #5236
• docs: Update runtime explanations by @Sherlock113 in #5240
• fix(regression): call error when context parameter is present by @frostming in #5247

Full Changelog: v1.4.0...v1.4.1

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 code command 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.PythonImage for defining the Bento runtime environment in Python instead of using bentofile.yaml or pyproject.toml
• Support customizing runtime configurations (e.g., Python version, system packages, and dependencies) directly in the service.py file
• Introduced context-sensitive run() method for running custom build commands
• Backward compatible with existing bentofile.yaml and pyproject.toml configurations

⚡ 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.HuggingFaceModel for loading models from HF. It supports private model repositories and custom endpoints
• Added bentoml.models.BentoModel for 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.Service API (with runners) is now officially deprecated and is scheduled for removal in a future release. We recommend you use the @bentoml.service decorator.

---

Note that:

• 1.4 remains fully compatible with Bentos created by 1.3.
• 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 #5208
• feat(service): expose service-level labels definition by @aarnphm in #5211
• fix: restore path after import by @frostming in #5214
• fix: compile bytecode when installing python packages by @frostming in #5212
• fix: IO descriptor honor validators by @frostming in #5213
• feat(image): add support for chaining .pyproject.toml by @aarnphm in #5218
• feat: support root input spec using positonal-only argument by @frostming in #5217
• fix: gradio error when uploading file by @frostming in #5220
• fix: input data validation for root input by @frostming in #5221
• fix: don't restore model store after importing service by @frostming in #5223
• feat(metrics): extend histogram buckets to support LLM latencies by @devin-ai-integration in #5222
• fix: always add bentoml req unless it is specified as a url dependency by @frostming in #5225
• docs: update links to examples by @aarnphm in #5224
• docs: add environment variable authentication documentation by @devin-ai-integration in #5231
• docs: Update docs to use new runtime API by @Sherlock113 in #5177
• fix: add files under env/docker by @frostming in #5234

Full Changelog: v1.3.22...v1.4.0

v1.4.0a2

What's Changed

• fix: restore path after import by @frostming in #5214

Full Changelog: v1.4.0a1...v1.4.0a2

v1.4.0a1

What's Changed

• feat: support bentoml serve without service name by @frostming in #5208
• feat(service): expose service-level labels definition by @aarnphm in #5211

Full Changelog: v1.3.22...v1.4.0a1