1 Release published by 1 person

• v0.3.1 0.3.1

  published May 27, 2025

1 Pull request opened by 1 person

• Hacky tensor parallel for Vision Models

  #791 opened May 25, 2025

2 Issues closed by 2 people

• [BUG] Remove Sentencepiece

  #789 closed May 27, 2025

• [REQUEST] Support new SOTA vision model: Qwen 2.5 VL (3B, 7B, 72B)

  #724 closed May 26, 2025

2 Issues opened by 2 people

• [QUESTION] Estimate measurements and quantization peak VRAM use in advance

  #792 opened May 26, 2025

• [BUG] Silent crash in safetensors call when compiling shards

  #790 opened May 25, 2025