Starstruk Logo MarkStarstruk

v0.2.81

rajnandan1/kenerv0.2.81Feb 18, 2026by akaashrp

AI Summary

A major overhaul of the web-llm engine and API, featuring a new architecture with OpenAI API compatibility, expanded model support including vision models, and improved WebGPU performance.

Key Highlights

  • Engine and API overhaul with multi-model loading support.
  • OpenAI API compatibility including chat, function calling, and embeddings.
  • Expanded prebuilt model support (Llama, Mistral, Qwen, Phi, and Vision).
  • WebGPU performance improvements and support for IndexedDB caching.

New Features

  • OpenAI API mirroring
  • XGrammar integration for constrained generation
  • TVM-FFI integration
  • IndexedDB caching
  • RAG/doc-chat examples

Full Release Notes

* Engine and API overhaul: ChatModule refactored into Engine/MLCEngine, consolidated constructor/reload behavior, multi-model loading, better worker lifecycle, concurrency handling
* OpenAI API: mirror chat/completions APIs, stateful options, function calling and embeddings support
* Conversation templates: unified conversation template schema with custom templates
* Expanded prebuilt model support: added support for more models (Llama 2/3/3.1/3.2, Mistral variants, Gemma 2, Qwen2/2.5/3, Phi family, including vision)
* Runtime and caching: WebGPU performance/reliability improvements (more GPU-side kernels, better OOM/deviceLost handling), wasm/prebuilt versioning updates, support IndexedDB caching
* XGrammar integration: JSON-schema/grammar-constrained generation, XGrammar structural tag
* TVM-FFI integration: refactor for compatibility with more recent TVM commits and TVM FFI 
* Examples: ServiceWorkerEngine + updated Chrome extension demos, new RAG/doc-chat examples, tool calls via structural tag
* CI: GitHub actions for linting and pre-commit hooks 

**Full Changelog**: https://github.com/mlc-ai/web-llm/compare/v0.2.0...v0.2.81