3 people a3c83ff2fd Faster per-token fp8 group quant packed kernel for blackwell (#41326) ...

Signed-off-by: Yongye Zhu <[email protected]>
Co-authored-by: Roger Wang <[email protected]>

2026-04-30 18:09:55 -07:00

..

cutlass_extensions/epilogue

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

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

quantization

Faster per-token fp8 group quant packed kernel for blackwell (#41326)

2026-04-30 18:09:55 -07:00

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