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-tile.cuh
+1 -7
View File
@@ -1,6 +1,5 @@
#include "common.cuh"
#include "fattn-common.cuh"
#include "fattn-wmma-f16.cuh"
// nbatch_fa == number of KQ rows to process per iteration
// nbatch_K == number of K columns to load in parallel for KQ calculation
@@ -825,12 +824,7 @@ static __global__ void flash_attn_tile(
// Skip unused kernel variants for faster compilation:
if (
#ifdef GGML_USE_WMMA_FATTN
(ncols2 != 1 && DV != 40 && DV != 72 && DV != 512) ||
#endif // GGML_USE_WMMA_FATTN
(use_logit_softcap && !(DV == 128 || DV == 256 || DV == 512))
) {
if ((use_logit_softcap && !(DV == 128 || DV == 256 || DV == 512))) {
GGML_UNUSED_VARS(Q, K, V, mask, sinks, KV_max, dst, dst_meta, scale,
max_bias, m0, m1, n_head_log2, logit_softcap,
ne00, ne01, ne02, ne03,