Starstruk Logo MarkStarstruk

v0.2.81

trycompai/compv0.2.81Feb 18, 2026by akaashrp

AI Summary

Performs a major overhaul of the engine and API, mirrors OpenAI chat/completions APIs, expands prebuilt model support, and improves WebGPU performance.

Key Highlights

  • Engine and API refactored
  • OpenAI API mirroring
  • Expanded model support
  • WebGPU performance improvements
  • XGrammar integration

Breaking Changes

  • Engine and API overhaul
  • ChatModule refactored into Engine/MLCEngine

New Features

  • OpenAI API mirroring
  • Function calling support
  • Embeddings support
  • Conversation templates
  • Expanded model support
  • WebGPU reliability improvements
  • IndexedDB caching
  • XGrammar integration
  • TVM-FFI integration
  • New 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