ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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) {