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

HIP: RDNA4 tensor core support for MMF (#17077)

Browse Source 
* mmf for rdna4

* align the padding for rdna4

* forbit mul_mat_f for rdna4

* fix as comment

* remove device kernels

* add constexpr for early return

* update based on review comment

* change based on the review comment

* pass compile error

* keep code consistency

---------

Co-authored-by: zhang hui <you@example.com>
This commit is contained in:
yulo
2025-11-22 00:03:24 +01:00
committed by GitHub
co-authored by zhang hui
parent 8e9ddba610
commit 028f93ef98
5 changed files with 180 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/mmf.cu
+3 -3
View File
@@ -151,7 +151,7 @@ bool ggml_cuda_should_use_mmf(enum ggml_type type, int cc, int warp_size, const
return false;
}
} else {
if (src1_ncols > 16) {
if (src1_ncols > 16 || GGML_CUDA_CC_IS_RDNA4(cc)) {
return false;
}
}
@@ -160,9 +160,9 @@ 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);
return volta_mma_available(cc) || turing_mma_available(cc) || amd_wmma_available(cc);
case GGML_TYPE_BF16:
return ampere_mma_available(cc);
return ampere_mma_available(cc) || amd_wmma_available(cc);
default:
return false;
}