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

HIP: remove rocWMMA FlashAttention (#26046)

Browse Source
This commit is contained in:
Johannes Gäßler
2026-07-24 17:53:54 +02:00
committed by GitHub
parent ed7adbfefd
commit fa72aeccb2
10 changed files with 5 additions and 798 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/fattn.cu
+4 -18
View File
@@ -3,7 +3,6 @@
#include "fattn-mma-f16.cuh"
#include "fattn-tile.cuh"
#include "fattn-vec.cuh"
#include "fattn-wmma-f16.cuh"
#include "fattn.cuh"
template <int DKQ, int DV, int ncols2>
@@ -330,11 +329,10 @@ static void ggml_cuda_flash_attn_ext_vec(ggml_backend_cuda_context & ctx, ggml_t
// Best FlashAttention kernel for a specific GPU:
enum best_fattn_kernel {
BEST_FATTN_KERNEL_NONE = 0,
BEST_FATTN_KERNEL_TILE = 200,
BEST_FATTN_KERNEL_VEC = 100,
BEST_FATTN_KERNEL_WMMA_F16 = 300,
BEST_FATTN_KERNEL_MMA_F16 = 400,
BEST_FATTN_KERNEL_NONE = 0,
BEST_FATTN_KERNEL_TILE = 200,
BEST_FATTN_KERNEL_VEC = 100,
BEST_FATTN_KERNEL_MMA_F16 = 400,
};
static bool ggml_cuda_fattn_kv_type_supported(ggml_type type) {
@@ -500,14 +498,6 @@ static best_fattn_kernel ggml_cuda_get_best_fattn_kernel(const int device, const
return BEST_FATTN_KERNEL_MMA_F16;
}
// Use the WMMA kernel if possible:
if (ggml_cuda_should_use_wmma_fattn(cc) && K->ne[1] % FATTN_KQ_STRIDE == 0 && Q->ne[0] != 40 && Q->ne[0] != 72 && Q->ne[0] != 192 && Q->ne[0] != 512 && Q->ne[0] != 576) {
if (can_use_vector_kernel && Q->ne[1] <= 2) {
return BEST_FATTN_KERNEL_VEC;
}
return BEST_FATTN_KERNEL_WMMA_F16;
}
// AMD MFMA needs a certain minimum batch size to outscale the tile kernel for large head sizes.
if ((amd_mfma_available(cc) && Q->ne[0] <= 256) && Q->ne[0] != 40 && Q->ne[0] != 72) {
if ((Q->ne[0] <= 64 && Q->ne[1] * gqa_ratio_eff > 8)) {
@@ -559,7 +549,6 @@ size_t ggml_cuda_flash_attn_ext_get_alloc_size(int device, const ggml_tensor * d
switch (kernel) {
case BEST_FATTN_KERNEL_TILE:
case BEST_FATTN_KERNEL_WMMA_F16:
case BEST_FATTN_KERNEL_MMA_F16:
need_f16_K = true;
need_f16_V = true;
@@ -589,9 +578,6 @@ void ggml_cuda_flash_attn_ext(ggml_backend_cuda_context & ctx, ggml_tensor * dst
case BEST_FATTN_KERNEL_VEC:
ggml_cuda_flash_attn_ext_vec(ctx, dst);
break;
case BEST_FATTN_KERNEL_WMMA_F16:
ggml_cuda_flash_attn_ext_wmma_f16(ctx, dst);
break;
case BEST_FATTN_KERNEL_MMA_F16:
ggml_cuda_flash_attn_ext_mma_f16(ctx, dst);
break;