Repository navigation
qwen3_5 cuda: 2, 3, 5 and 6-bit tiles of their own width and a prompt GEMM for them (27B oQ2 on 16 GB) - #859
Merged
Merged
Commits
Commits on Oct 16, 2026
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed