{"full_name":"mlc-ai/web-llm","owner":"mlc-ai","name":"web-llm","shard":"1","url":"https://github.com/mlc-ai/web-llm","description":"High-performance In-browser LLM Inference Engine ","homepage":"https://webllm.mlc.ai","topics":["deep-learning","llm","tvm","webgpu","webml","chatgpt","language-model"],"tag_pages":["chatgpt","deep-learning","language-model","llm","webgpu"],"language":"TypeScript","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/106173866?v=4","created_at":"2023-04-13T18:11:59Z","pushed_at":"2026-11-15T19:09:56Z","metrics":{"stars":19379,"forks":1412,"watchers":137,"issues":449,"prs":441,"releases":8,"issues_open":137,"issues_closed":312,"prs_open":21,"prs_closed":46,"prs_merged":374,"discussions":0},"growth":{"day":{"stars":2,"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":[19365,19368,19372,19373,19375,19377,19379],"forks":[1410,1410,1411,1412,1413,1412,1412],"watchers":[null,137,137,137,137,137,137],"issues_open":[null,136,136,136,136,137,137],"prs_open":[null,16,17,17,17,18,21]},"boards":{},"same_owner":[{"full_name":"mlc-ai/mlc-llm","name":"mlc-llm","shard":"1","boards":{}}],"issues":[{"number":553,"title":"Use subgroup operations when possible","comments":23,"created_at":"2024-08-20T11:30:40Z"},{"number":524,"title":"Gemma 2 2B crashes on mobile phone","comments":16,"created_at":"2024-08-04T21:13:12Z"},{"number":810,"title":"[Model Request] Gemma 4","comments":12,"created_at":"2026-04-03T13:58:25Z"},{"number":609,"title":"WebLLM always processes on Intel UHD Graphics, not on NVIDIA T1200","comments":11,"created_at":"2024-10-10T06:47:50Z"},{"number":519,"title":"Phi 3 Mini output near random (Phi-3-mini-4k-instruct-q4f16_1-MLC)","comments":11,"created_at":"2024-07-28T18:29:17Z"},{"number":319,"title":"GPU Device Error: Uncaught (in promise) TypeError: lib$1.exports.detectGPUDevice is not a function","comments":10,"created_at":"2024-02-28T11:22:46Z"},{"number":675,"title":"Model Request: Gemma 3","comments":8,"created_at":"2025-03-12T10:10:12Z"},{"number":680,"title":"I downloaded the model on huggingface locally, can I load the local model?","comments":7,"created_at":"2025-04-03T11:00:15Z"}],"discussions":[],"latest_release":{"name":"v0.2.88","tag":"v0.2.88","published_at":"2026-11-10T09:20:02Z","body":"* Fix prompt echo in streaming text completions\n* Fix selected-token logprobs and logprobs for buffered UTF-8 output\n* Fix decode rates for completions that finish during prefill\n* Fix TypeScript type checking for installed packages\n* Upgrade `@mlc-ai/web-runtime` to `0.28.0-dev2`\n\n**Full Changelog**: https://github.com/mlc-ai/web-llm/compare/v0.2.87...v0.2.88\n","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}