3 Pull requests merged by 3 people

• Update README.md

  #1667 merged Jul 31, 2025

• Fix minor typo on README.md

  #1664 merged Jul 31, 2025

• Enable pytorch fused op on XPU

  #1660 merged Jul 31, 2025

3 Issues opened by 3 people

• [BUG] Tensor mismatch on a lot of models

  #1668 opened Aug 3, 2025

• [support] please add Windows + Intel XPU support

  #1666 opened Jul 31, 2025

• [BUG] qwen3 quantization error and how to fix：RuntimeError: The size of tensor a (32) must match the size of tensor b

  #1665 opened Jul 30, 2025

2 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• [BUG] memory leak when quantizing Gemma 3

  #1636 commented on Jul 28, 2025 • 0 new comments

• [BUG] Quantizing Qwen2.5-VL-7B on 4090 got VRAM oom

  #1658 commented on Jul 29, 2025 • 0 new comments