tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-21 15:13:07 -04:00
Code Issues Packages Projects Releases Wiki Activity

HIP: remove the use of __HIP_PLATFORM_AMD__, explicitly support only AMD targets (#14945)

Browse Source
This commit is contained in:
uvos
2025-07-29 20:23:04 +02:00
committed by GitHub
parent b77d11179d
commit aa79524c51
10 changed files with 67 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/fattn-common.cuh
View File

@@ -592,9 +592,9 @@ static __global__ void flash_attn_stream_k_fixup(
}
template<int D> // D == head size
#if !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__))
#if !defined(GGML_USE_HIP)
__launch_bounds__(D, 1)
#endif // !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__))
#endif // !(defined(GGML_USE_HIP)
static __global__ void flash_attn_combine_results(
const float * __restrict__ VKQ_parts,
const float2 * __restrict__ VKQ_meta,