Skip to content

[Kernel] Enable FP8 Cutlass for Ada Lovelace #6950

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jul 31, 2024
Merged

[Kernel] Enable FP8 Cutlass for Ada Lovelace #6950

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 1 addition & 7 deletions csrc/quantization/cutlass_w8a8/scaled_mm_entry.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,13 +38,7 @@ bool cutlass_scaled_mm_supports_fp8(int64_t cuda_device_capability) {
if (cuda_device_capability >= 90) {
return CUDA_VERSION >= 12000;
} else if (cuda_device_capability >= 89) {
// CUTLASS Kernels have not been tuned for Ada Lovelace systems
// and are slower than torch.mm. Return false unconditionally in this case.
return false;

// Once the CUTLASS kernels have been optimized for Lovelace systems,
// use the following check:
// return CUDA_VERSION >= 12040;
return CUDA_VERSION >= 12040;
}
#endif

Expand Down