tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-30 22:23:31 -04:00
Code Issues Packages Projects Releases Wiki Activity

HIP: Add support for RDNA4 targets (#12372)

Browse Source
This commit is contained in:
Slobodan Josic
2025-03-26 23:46:30 +01:00
committed by GitHub
parent b3298fa47a
commit bd40678df7
7 changed files with 25 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/mmq.cuh
View File

@@ -2577,9 +2577,9 @@ static __device__ void mul_mat_q_process_tile(
template <ggml_type type, int mmq_x, int nwarps, bool need_check>
#if defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__)
#if defined(RDNA3) || defined(RDNA2) || defined(CDNA) || defined(GCN)
#if defined(RDNA4) || defined(RDNA3) || defined(RDNA2) || defined(CDNA) || defined(GCN)
__launch_bounds__(WARP_SIZE*nwarps, 2)
#endif // defined(RDNA3) || defined(RDNA2) || defined(CDNA) || defined(GCN)
#endif // defined(RDNA4) || defined(RDNA3) || defined(RDNA2) || defined(CDNA) || defined(GCN)
#else
#if __CUDA_ARCH__ >= GGML_CUDA_CC_VOLTA
__launch_bounds__(WARP_SIZE*nwarps, 1)