Skip to content

[None][fix] Remove clone in fp8 quant. #12687

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
Tracin merged 3 commits into from
Apr 7, 2026
Merged

[None][fix] Remove clone in fp8 quant. #12687

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6967761
Remove clone in fp8 quant.
Tracin Apr 2, 2026
c0498ab
Fix.
Tracin Apr 7, 2026
4400b39
Merge branch 'main' into remove_clone_fp8
Tracin Apr 7, 2026
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
11 changes: 6 additions & 5 deletions cpp/tensorrt_llm/thop/fp8Op.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,11 +111,12 @@ std::tuple<Tensor, Tensor> e4m3_quantize_helper(Tensor input, at::optional<Tenso

if (scales.has_value())
{
// static quantization will use float scales by default.
scales_ = scales.value().clone();
CHECK_TH_CUDA(scales_);
CHECK_TYPE(scales_, torch::kFloat32);
e4m3_static_quantize(input, quantized_input, scales_, stream, quantize_mode);
// static quantization will use float scales by default and output scales_ will be ignored.
scales_
Comment thread
Tracin marked this conversation as resolved.
= torch::empty_like(scales.value(), torch::dtype(input.dtype()).device(torch::kCUDA).requires_grad(false));
CHECK_TH_CUDA(scales.value());
CHECK_TYPE(scales.value(), torch::kFloat32);
e4m3_static_quantize(input, quantized_input, scales.value(), stream, quantize_mode);
}
else
{
Expand Down
Loading