Wentao Ye 0d453e2336 [Perf] Batch invariance with Cutlass fp8 support, 28.9% E2E latency improvement (#40408) ...

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

2026-05-11 12:20:58 -04:00

..

cutlass_extensions/epilogue

[3/n] Migrate cutlass/scaled_mm_entry.cu torch stable ABI (#37221)

2026-03-30 11:20:13 -07:00

quantization

[Perf] Batch invariance with Cutlass fp8 support, 28.9% E2E latency improvement (#40408)

2026-05-11 12:20:58 -04:00

dispatch_utils.h

[4/n] Migrate FP4/W4A8 CUTLASS kernels to torch stable ABI (#37503)

2026-03-31 10:21:13 -07:00

ops.h

[Bugfix] Guard mxfp4_experts_quant bindings on ENABLE_NVFP4_SM100 (#40191)

2026-04-18 13:58:46 -07:00

permute_cols.cu

[1/n] Migrate permute_cols to libtorch stable ABI (#31509)

2026-03-19 11:27:26 -04:00

torch_bindings.cpp

[Bugfix] Guard mxfp4_experts_quant bindings on ENABLE_NVFP4_SM100 (#40191)

2026-04-18 13:58:46 -07:00

torch_utils.h

[4/n] Migrate FP4/W4A8 CUTLASS kernels to torch stable ABI (#37503)

2026-03-31 10:21:13 -07:00