web-llm · Issues· 152 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #853
Exposing a compatible interface for Chrome Built-in AI (Prompt API) / Polyfill
Updated Sep 14, 2026 - #857
[Feature Request] configurable download threads
Updated Sep 12, 2026 - #844
[Bug] shapeCache LRU eviction disposes in-use ShapeTuples → "Object has already been disposed" → GPU device hang (regression introduced in 0.2.83)
Updated Aug 18, 2026 - #840
[Feature Request] Speculative decoding (draft model + batched verification) in the web runtime
Updated Aug 18, 2026 - #847
Feature request
Updated Aug 17, 2026 - #810
[Model Request] Gemma 4
Updated Aug 14, 2026 - #644
Error: Cannot initialize runtime because of requested maxComputeWorkgroupStorageSize exceeds limit. requested=32768, limit=16384.
Updated Aug 3, 2026 - #836
[Bug] WebLLM Engine Initialization Fails on Qualcomm Adreno GPUs with VK_ERROR_DEVICE_LOST
Updated Jul 25, 2026 - #741
Firefox Webpack Size Exceeds Limit
Updated Jul 3, 2026 - #707
Roadmap
Updated Jun 12, 2026 - #786
Model request: Granite 4.0
Updated Jun 10, 2026 - #719
Support for embedding gemma
Updated Jun 6, 2026 - #828
what 1984 Right Think "suggestions" are inflicted?
Updated Jun 6, 2026 - #711
docs: WebLLM model provider for the Vercel AI SDK
Updated May 27, 2026 - #807
[Bug] xgrammar GrammarMatcher crashes with invalid token id when using JSON Schema mode (Qwen3-0.6B)
Updated Apr 29, 2026