Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

HIP: enable mmf for RDNA3 (#17879)

Browse Source 
* enable mmf for RDNA3

* disable mmf for some shape

* move some mmvf to mmf

* more mmfv to mmf

* 3 is good in mmvf

---------

Co-authored-by: zhang hui <you@example.com>
This commit is contained in:
yulo
2025-12-12 11:34:33 +01:00
committed by GitHub
co-authored by zhang hui
parent a81a569577
commit c33a58bced
4 changed files with 84 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/mmf.cu
+5 -3
View File
@@ -151,7 +151,9 @@ bool ggml_cuda_should_use_mmf(enum ggml_type type, int cc, int warp_size, const
return false;
}
} else {
if (src1_ncols > 16) {
if (GGML_CUDA_CC_IS_RDNA3_0(cc) && src1_ncols > 8) {
return false;
} else if (src1_ncols > 16) {
return false;
}
}
@@ -160,9 +162,9 @@ bool ggml_cuda_should_use_mmf(enum ggml_type type, int cc, int warp_size, const
case GGML_TYPE_F32:
return ampere_mma_available(cc);
case GGML_TYPE_F16:
return volta_mma_available(cc) || turing_mma_available(cc) || (amd_wmma_available(cc) && GGML_CUDA_CC_IS_RDNA4(cc));
return volta_mma_available(cc) || turing_mma_available(cc) || amd_wmma_available(cc);
case GGML_TYPE_BF16:
return ampere_mma_available(cc) || (amd_wmma_available(cc) && GGML_CUDA_CC_IS_RDNA4(cc));
return ampere_mma_available(cc) || amd_wmma_available(cc);
default:
return false;
}