Yongye ZhuandClaude ec0a31d4aa [Bugfix][Kernel] Fix mHC fused-RMSNorm big-fuse miscompile for hidden_size != 4096 (#44692) ...

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>

2026-06-06 10:44:21 +08:00

..

__init__.py

[Bugfix] [ROCm] [DSV4] [Perf] Add aiter mhc support (#41946)

2026-05-13 21:43:15 +08:00

aiter.py

[Bugfix] [ROCm] [DSV4] [Perf] Add aiter mhc support (#41946)

2026-05-13 21:43:15 +08:00

tilelang_kernels.py

[Bugfix][Kernel] Fix mHC fused-RMSNorm big-fuse miscompile for hidden_size != 4096 (#44692)

2026-06-06 10:44:21 +08:00

tilelang.py

[DSv4] Move mHC tilelang kernels & Don't use CustomOP in dsv4/nvidia (#43905)

2026-05-29 10:25:02 +08:00

torch.py

[Bugfix] [ROCm] [DSV4] [Perf] Add aiter mhc support (#41946)

2026-05-13 21:43:15 +08:00

triton.py

[Bugfix] [ROCm] [DSV4] [Perf] Add aiter mhc support (#41946)

2026-05-13 21:43:15 +08:00