Skip to content
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

[Kernel] Update Cutlass int8 kernel configs for SM90 #5514

Merged
merged 7 commits into from
Jun 20, 2024
Merged

[Kernel] Update Cutlass int8 kernel configs for SM90 #5514

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
2748e67
Add h100 int8 configs
Jun 13, 2024
67409d3
format
Jun 14, 2024
012d1ad
whitespace change
Jun 14, 2024
71b6c88
clang-format
Jun 14, 2024
e070644
remove M and N from template params
Jun 18, 2024
872fede
format
Jun 18, 2024
19055e1
bug fix - get correct N
Jun 18, 2024
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
Prev Previous commit
Next Next commit
clang-format
  • Loading branch information
Varun Sundar Rabindranath committed Jun 14, 2024
commit 71b6c883967e83d62f55ff7c1cba20078a20cf5b
4 changes: 2 additions & 2 deletions csrc/quantization/cutlass_w8a8/scaled_mm_c3x.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -486,8 +486,8 @@ void cutlass_scaled_mm_sm90(torch::Tensor& out, torch::Tensor const& a,
out, a, b, a_scales, b_scales);
} else {
TORCH_CHECK(out.dtype() == torch::kFloat16);
return cutlass_gemm_sm90_fp8_dispatch<
cutlass::float_e4m3_t, cutlass::half_t, ScaledEpilogue>(
return cutlass_gemm_sm90_fp8_dispatch<cutlass::float_e4m3_t,
cutlass::half_t, ScaledEpilogue>(
out, a, b, a_scales, b_scales);
}
}
Expand Down
Loading