iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix] hadacore_transform: respect inplace parameter to fix garbage outputs with QuIP transforms (#43462)

Browse Source 
Signed-off-by: Gilles Turpin <turpingilles15@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
Gilles Turpin
2026-09-22 12:48:20 -04:00
committed by GitHub
co-authored by Wentao Ye
parent a6131b0e65
commit 74370a0e30
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
csrc/libtorch_stable/quantization/hadamard/hadacore/hadamard_transform_cuda.cu
+1 -1
View File
@@ -796,7 +796,7 @@ torch::stable::Tensor hadacore_transform(torch::stable::Tensor& x, bool inplace)
VLLM_STABLE_DISPATCH_HALF_TYPES(x.scalar_type(), "hadacore_transform_runfht", [&] {
auto constexpr SCALAR_TYPE = torch::headeronly::CppTypeToScalarType<scalar_t>::value;
hadacore::run_fht<SCALAR_TYPE>(x.data_ptr(), x.data_ptr(), x.numel(), had_size, stream);
hadacore::run_fht<SCALAR_TYPE>(x.data_ptr(), out.data_ptr(), x.numel(), had_size, stream);
});
if (numel % 256 != 0) {