Feature request
Status: Open.
#847In mlc-ai/web-llm;
· Sallamhamza opened on Aug 17, 2026
[Bug] shapeCache LRU eviction disposes in-use ShapeTuples → "Object has already been disposed" → GPU device hang (regression introduced in 0.2.83)
Status: Open.
#844In mlc-ai/web-llm;
· YuWenYang1 opened on Aug 6, 2026
[Feature Request] Speculative decoding (draft model + batched verification) in the web runtime
Status: Open.
#840In mlc-ai/web-llm;
· Spitfire-Products opened on Jul 25, 2026
[Bug] WebLLM Engine Initialization Fails on Qualcomm Adreno GPUs with VK_ERROR_DEVICE_LOST
Status: Open.
#836In mlc-ai/web-llm;
· opnsrcntrbtr opened on Jun 21, 2026
what 1984 Right Think "suggestions" are inflicted?
Status: Open.
#828In mlc-ai/web-llm;
· gillateralleey opened on Jun 6, 2026
[Model Request] Gemma 4
Status: Open.
#810In mlc-ai/web-llm;
· jokctseng opened on Apr 3, 2026
[Bug] xgrammar GrammarMatcher crashes with invalid token id when using JSON Schema mode (Qwen3-0.6B)
Status: Open.
#807In mlc-ai/web-llm;
· wopelo opened on Apr 2, 2026
Request new model: PrismML Bonsai
Status: Open.
#801In mlc-ai/web-llm;
· julian-resimate opened on Apr 1, 2026
Feature: Resumable downloads and integrity verification for model files
Status: Open.
#800In mlc-ai/web-llm;
· hamzaydia opened on Apr 1, 2026
[Feature Request] Support for TurboQuant (PolarQuant + QJL) for 6x KV Cache Compression
Status: Open.
#799In mlc-ai/web-llm;
· rbf22 opened on Mar 31, 2026
🐛 Feature Request: Native Audio Input Support for WebLLM (Multimodal Voice Interface)
Status: Open.
#798In mlc-ai/web-llm;
· jxnding opened on Mar 29, 2026
Request new model Microsoft Bitnet
Status: Open.
#788In mlc-ai/web-llm;
· block0ps opened on Mar 19, 2026
