Skip to content

GitLab

Unverified Commit 40253bab authored by DefTruth's avatar DefTruth Committed by GitHub
Browse files

[Bugfix][W8A8] fixed cutlass block fp8 binding (#14796)

parent c77620d2
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
csrc/torch_bindings.cpp
View file @ 40253bab
...@@ -370,7 +370,7 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) { ...@@ -370,7 +370,7 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
"cutlass_scaled_mm_supports_block_fp8(int cuda_device_capability) -> " "cutlass_scaled_mm_supports_block_fp8(int cuda_device_capability) -> "
"bool"); "bool");
ops.impl("cutlass_scaled_mm_supports_block_fp8", ops.impl("cutlass_scaled_mm_supports_block_fp8",
&cutlass_scaled_mm_supports_fp8); &cutlass_scaled_mm_supports_block_fp8);
// Check if cutlass sparse scaled_mm is supported for CUDA devices of the // Check if cutlass sparse scaled_mm is supported for CUDA devices of the
// given capability // given capability
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment