Skip to content

[release/2.10] Fix int4mm device memcpy error on Windows (#175410) #3165

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
jeffdaily merged 1 commit into from
Apr 20, 2026
Merged

[release/2.10] Fix int4mm device memcpy error on Windows (#175410) #3165

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
7 changes: 7 additions & 0 deletions aten/src/ATen/native/cuda/int4mm.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -581,7 +581,14 @@ struct BLayout_TC_int4 {
// type pun, the __nv_bfloat162 value in bf16x2x4 is a struct and
// can't be used as a 32-bit asm register argument for `mma`
static_assert(sizeof(bf16x2x4) == sizeof(out[0][0]), "");
// On Windows with ROCm, std::memcpy resolves to a __host__-only
// function and cannot be called from __device__ code. Use the raw
// memcpy which the HIP compiler provides as a __device__ builtin.
#if defined(_WIN32) && defined(USE_ROCM)
memcpy(&out[i][j], &v, sizeof(bf16x2x4_u32));
#else
std::memcpy(&out[i][j], &v, sizeof(bf16x2x4_u32));
#endif
}
}
}
Expand Down