tiny-army / web /engineWebllm.js

Commit History

  1. Settings: model section to top; default WebLLM + Qwen3 0.6B; copyable debug⁠

    polats +1: Claude Opus 4.8 (1M context)
    898540a
  2. Cache status + delete for WebLLM and Transformers.js (like wllama)⁠

    polats +1: Claude Opus 4.8 (1M context)
    b0f48f8
  3. Fix Qwen3 on WebLLM: budget for thinking + capture reasoning_content⁠

    polats +1: Claude Opus 4.8 (1M context)
    eba5aae
  4. Fix Qwen3 parsing (/no_think) + WebLLM double-load guard & progress clarity⁠

    polats +1: Claude Opus 4.8 (1M context)
    ab87288
  5. Fix model re-downloads (persistent storage) + WebLLM shader-f16 crash⁠

    polats +1: Claude Opus 4.8 (1M context)
    fa27f81
  6. Multi-engine benchmark: wllama vs Transformers.js vs WebLLM (engine selector)⁠

    polats +1: Claude Opus 4.8 (1M context)
    f8d0843