biondizzle ae26f6b83c Fix dense router BF16 dispatch: use torch.matmul instead of F.linear ...

- F.linear(x, W) computes x @ W.T which caused shape mismatch when
  W_gate was pre-transposed to [E, H]
- Use torch.matmul(x, W_gate) instead — computes x @ W directly, no
  transpose needed, no FP32 conversion, fully graph-capturable
- W_gate stays as [H, E] (original checkpoint shape)

2026-06-04 05:58:24 +00:00

..

attention

Wire prefill FMHA into production.py and single_shot

2026-06-03 03:49:57 +00:00

cache

Cleanup Step 2: Archive Lineage P code, fix broken imports

2026-06-02 19:27:07 +00:00

compressor

Cleanup Step 2: Archive Lineage P code, fix broken imports

2026-06-02 19:27:07 +00:00

cuda

Add c10/cuda/CUDAStream.h include for getCurrentCUDAStream

2026-06-04 04:13:40 +00:00

gemm

Blackwell swizzle CUDA kernel for CUDA graph capture

2026-06-04 03:03:02 +00:00

indexer

Cleanup Step 2: Archive Lineage P code, fix broken imports

2026-06-02 19:27:07 +00:00

router

Fix dense router BF16 dispatch: use torch.matmul instead of F.linear

2026-06-04 05:58:24 +00:00

__init__.py

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00