{"full_name":"bentoml/BentoML","owner":"bentoml","name":"BentoML","shard":"1","url":"https://github.com/bentoml/BentoML","description":"The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!","homepage":"https://bentoml.com","topics":["model-serving","mlops","llmops","generative-ai","llm-inference","model-inference-service","inference-platform","deep-learning","llm-serving","machine-learning","python","multimodal","ml-engineering","llm","ai-inference"],"tag_pages":["deep-learning","generative-ai","llm","llm-inference","llm-serving","llmops","machine-learning","mlops","model-serving","multimodal","python"],"language":"Python","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/49176046?v=4","created_at":"2019-04-02T01:39:27Z","pushed_at":"2026-11-02T17:14:27Z","metrics":{"stars":8941,"forks":1065,"watchers":80,"issues":1186,"prs":4312,"releases":195,"issues_open":160,"issues_closed":1026,"prs_open":119,"prs_closed":549,"prs_merged":3644,"discussions":223},"growth":{"day":{"stars":0,"forks":0,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[8935,8941,8940,8940,8940,8941,8941],"forks":[1062,1064,1064,1064,1064,1065,1065],"watchers":[null,80,80,80,80,80,80],"issues_open":[null,160,160,160,160,160,160],"prs_open":[null,117,118,118,118,119,119]},"boards":{},"same_owner":[{"full_name":"bentoml/OpenLLM","name":"OpenLLM","shard":"1","boards":{}}],"issues":[{"number":4117,"title":"bug: containerize filed","comments":30,"created_at":"2023-08-11T13:54:01Z"},{"number":3669,"title":"bug: aiohttp.client_exceptions.ServerDisconnectedError: Server disconnected","comments":19,"created_at":"2023-03-14T10:09:43Z"},{"number":3787,"title":"bug: Http Server is not worked with Pytorch-Lightning without 'del sys.modules[\"prometheus_client\"]'","comments":18,"created_at":"2023-04-25T02:15:40Z"},{"number":5426,"title":"bug: Uneven request distribution across workers in BentoML service","comments":11,"created_at":"2025-08-06T06:30:58Z"},{"number":5466,"title":"feature: support for pylock.toml","comments":7,"created_at":"2025-09-12T09:52:37Z"},{"number":3463,"title":"feature: Allow for New relic integration","comments":7,"created_at":"2023-01-20T17:29:30Z"},{"number":3200,"title":"bug:  Batching async run issue ","comments":7,"created_at":"2022-11-08T13:30:42Z"},{"number":2693,"title":"feat: ONNX-mlir","comments":6,"created_at":"2022-07-05T14:04:18Z"}],"discussions":[{"number":5748,"title":"BentoML CLI included in AgentManager's tool catalog","comments":0,"category":"Show and tell","created_at":"2026-10-18T10:21:31Z"},{"number":5635,"title":"MCP to help OSS devs understand bentoml/BentoML","comments":0,"category":"General","created_at":"2026-06-12T11:55:31Z"},{"number":5623,"title":"image tiling for deployment","comments":2,"category":"Q&A","created_at":"2026-05-31T15:14:14Z"},{"number":5574,"title":"ORCH — CLI runtime for orchestrating AI agent teams (Claude Code, Codex, Cursor)","comments":0,"category":"Show and tell","created_at":"2026-03-17T15:07:35Z"},{"number":5545,"title":"Posting content SSE conform with bentoml","comments":3,"category":"Q&A","created_at":"2026-02-05T20:26:19Z"},{"number":5422,"title":"Help needed:: Guidance on Deploying to Modern BentoCloud","comments":2,"category":"Q&A","created_at":"2025-07-27T23:13:12Z"},{"number":5367,"title":"Provide a predictable container path for secrets","comments":3,"category":"Ideas","created_at":"2025-05-21T08:22:28Z"},{"number":5325,"title":"BentoML code evolution","comments":2,"category":"Show and tell","created_at":"2025-04-18T18:48:39Z"}],"latest_release":{"name":"v1.4.40","tag":"v1.4.40","published_at":"2026-10-23T19:51:33Z","body":"## Security: eMudhra intermediate CA compromise\n\n- **\\`certifi>=2026.10.19\\`** is now required. It drops trust in the compromised eMudhra/emSign CAs.\n- Generated Dockerfiles and local \\`bentoml build\\` install **\\`uv==0.13.4\\` with \\`--require-hashes\\`** whenever uv is missing or older (uv < 0.13.4 bundles the compromised CAs). pip 26.2.2 is used where supported. (#5757)\n\n**Action for users:** run \\`bentoml build\\` again with 1.4.40, then redeploy, so your bento image picks up the fixed certifi and uv.\n\n## Also in this release\n\n- Agent skills for creating BentoML projects and for deploying to Kubernetes and EC2 (#5705, #5683)\n- Windows tar symlink extraction and fastai CI dependency resolution fix (#5689)\n- Docs and CI updates (#5710, #5715, #5741, #5702, #5758, #5759, #5760)\n\n**Full Changelog**: https://github.com/bentoml/BentoML/compare/v1.4.39...v1.4.40","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}