CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-13 10:57:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

HIP: fix flash_attn_stream_k_fixup warning (#11604)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-02-02 23:48:29 +01:00
committed by GitHub
parent 396856b400
commit 6eecde3cc8
2 changed files with 12 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/softmax.cu
View File

@@ -18,7 +18,7 @@ __device__ float __forceinline__ t2f32<half>(half val) {
#ifdef __clang__
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wpass-failed"
#endif
#endif // __clang__
template <bool use_shared, int ncols_template, int block_size_template, typename T>
static __global__ void soft_max_f32(
const float * x, const T * mask, float * dst, const int ncols_par, const int nrows_y,
@@ -126,7 +126,7 @@ static __global__ void soft_max_f32(
}
#ifdef __clang__
#pragma clang diagnostic pop
#endif
#endif // __clang__
static __global__ void soft_max_back_f32(
const float * grad, const float * dstf, float * dst, const int ncols, const float scale) {