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

[MUSA] enable fp16/fast_fp16/bf16_mma on PH1 (#17551)

Browse Source 
* [MUSA] enable fp16/fast_fp16/bf16_mma on PH1

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* Update ggml/src/ggml-cuda/fattn-vec.cuh

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* Update ggml/src/ggml-cuda/fattn-vec.cuh

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* Update ggml/src/ggml-cuda/fattn-tile.cuh

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* Address review comments

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
R0CKSTAR
2025-11-28 14:08:29 +01:00
committed by GitHub
co-authored by Johannes Gäßler
parent 2e7ef98f18
commit c6f7a423c8
5 changed files with 21 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/fattn-vec.cuh
+2 -2
View File
@@ -155,7 +155,7 @@ static __global__ void flash_attn_ext_vec(
for (int i0 = 0; i0 < int(D/sizeof(int)); i0 += WARP_SIZE) {
const int i = i0 + threadIdx.x;
if (i0 + WARP_SIZE <= D/sizeof(int) || i < D/sizeof(int)) {
if (i0 + WARP_SIZE <= int(D/sizeof(int)) || i < int(D/sizeof(int))) {
tmp_q_i32[i] = 0;
}
}
@@ -272,7 +272,7 @@ static __global__ void flash_attn_ext_vec(
KQ_max_new[j] = fmaxf(KQ_max_new[j], sum);
if ((nthreads_KQ == WARP_SIZE ? threadIdx.x : threadIdx.x % nthreads_KQ) == i_KQ_0) {
if ((nthreads_KQ == WARP_SIZE ? threadIdx.x : threadIdx.x % nthreads_KQ) == uint32_t(i_KQ_0)) {
KQ_reg[j] = sum;
}
}