Skip to content

HIP: Ignore unsupported unroll transformation in fattn-vec #14931

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 29, 2025
Merged

HIP: Ignore unsupported unroll transformation in fattn-vec #14931

Show file tree
Hide file tree
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
9 changes: 9 additions & 0 deletions ggml/src/ggml-cuda/fattn-vec-f16.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,12 @@
#include "common.cuh"
#include "fattn-common.cuh"

// Currenlty llvm with the amdgcn target dose not support unrolling loops
// that contain a break that can not be resolved at compile time.
#ifdef __clang__
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wpass-failed"
#endif // __clang__
template<int D, int ncols, ggml_type type_K, ggml_type type_V, bool use_logit_softcap> // D == head size
#ifndef GGML_USE_HIP
__launch_bounds__(D, 1)
Expand Down Expand Up @@ -341,6 +347,9 @@ static __global__ void flash_attn_vec_ext_f16(
NO_DEVICE_CODE;
#endif // defined(FLASH_ATTN_AVAILABLE) && defined(FP16_AVAILABLE)
}
#ifdef __clang__
#pragma clang diagnostic pop
#endif // __clang__

template <int D, int cols_per_block, ggml_type type_K, ggml_type type_V, bool use_logit_softcap>
void ggml_cuda_flash_attn_ext_vec_f16_case_impl(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
Expand Down
9 changes: 9 additions & 0 deletions ggml/src/ggml-cuda/fattn-vec-f32.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,12 @@
#include "common.cuh"
#include "fattn-common.cuh"

// Currenlty llvm with the amdgcn target dose not support unrolling loops
// that contain a break that can not be resolved at compile time.
#ifdef __clang__
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wpass-failed"
#endif // __clang__
template<int D, int ncols, ggml_type type_K, ggml_type type_V, bool use_logit_softcap> // D == head size
#ifndef GGML_USE_HIP
__launch_bounds__(D, 1)
Expand Down Expand Up @@ -336,6 +342,9 @@ static __global__ void flash_attn_vec_ext_f32(
NO_DEVICE_CODE;
#endif // FLASH_ATTN_AVAILABLE
}
#ifdef __clang__
#pragma clang diagnostic pop
#endif // __clang__

template <int D, int cols_per_block, ggml_type type_K, ggml_type type_V, bool use_logit_softcap>
void ggml_cuda_flash_attn_ext_vec_f32_case_impl(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
Expand Down
Loading