tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-29 13:43:38 -04:00
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

10
ggml/src/ggml-cuda/fattn-common.cuh
View File

@@ -516,6 +516,12 @@ constexpr __device__ dequantize_1_f32_t get_dequantize_1_f32(ggml_type type_V) {
nullptr;
}
// The HIP compiler for some reason complains that it can't unroll a loop because of the jt*ncols + j >= ne01 conditional.
#ifdef __clang__
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wpass-failed"
#endif // __clang__
template<int D, int ncols, int KQ_stride> // D == head size
#if !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__))
__launch_bounds__(D, 1)
@@ -614,6 +620,10 @@ static __global__ void flash_attn_stream_k_fixup(
}
}
#ifdef __clang__
#pragma clang diagnostic pop
#endif // __clang__
template<int D, int parallel_blocks> // D == head size
#if !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__))
__launch_bounds__(D, 1)