Skip to content

ChatLLM Web v2.0.0

Choose a tag to compare

View all tags
@Ryan-yang125 Ryan-yang125 released this 11 Aug 11:05
· 6 commits to main since this release
v2.0.0
0218530
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

ChatLLM Web 2.0 is a complete rebuild for private, browser-native AI chat.

Highlights

  • New Motion Lexicon v4 interface with responsive desktop and mobile layouts
  • Current MLC WebLLM runtime with Llama 3.2 1B and an approximately 880 MB first download
  • Web Worker inference with streaming Markdown, syntax highlighting, and math rendering
  • Local conversations, search, Command-K palette, keyboard shortcuts, dark mode, and PWA support
  • Production deployment on Cloudflare Pages

Breaking changes

  • Removed the old Next.js, DaisyUI, Vicuna 7B, and bundled 2023 WebLLM paths
  • Requires Node.js 20 or newer for local development
  • Requires a current WebGPU-capable Chrome or Edge browser for inference

Links

Validation

  • TypeScript, ESLint, and Vitest passed
  • Production build completed successfully
  • Production dependency audit reports zero vulnerabilities
  • Desktop, mobile, command palette, theme, and model load/cancel flows were browser-tested
Assets 2
Loading