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

vulkan: fix fp16 Flash Attention on Windows AMD RDNA2 and below (#19921)

Browse Source
This commit is contained in:
Ruben Ortlam
2026-02-26 19:11:04 +01:00
committed by GitHub
parent 37964f44f9
commit 723c71064d
3 changed files with 22 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-vulkan/vulkan-shaders/flash_attn.comp
+8 -1
View File
@@ -465,7 +465,14 @@ void main() {
if (SubGroupSize > 0) {
[[unroll]] for (uint s = D_split; s < SubGroupSize; s *= 2) {
Of[r][d] += subgroupShuffleXor(Of[r][d], s);
if (!OLD_AMD_WINDOWS) {
Of[r][d] += subgroupShuffleXor(Of[r][d], s);
} else {
// Something about f16vec4 subgroupShuffleXor is broken on AMD Windows RDNA2 and below.
// Shuffle full vec4 as workaround.
// See https://github.com/ggml-org/llama.cpp/issues/19881#issuecomment-3958643697
Of[r][d] += FLOAT_TYPEV4(subgroupShuffleXor(vec4(Of[r][d]), s));
}
}
if (row_split == 1) {
barrier();
ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_base.glsl
+4 -3
View File
@@ -14,9 +14,10 @@ layout (constant_id = 9) const uint32_t SHMEM_STAGING = 0;
layout (constant_id = 10) const uint32_t Flags = 0;
layout (constant_id = 11) const uint32_t LIMIT_OCCUPANCY_SHMEM = 0;
const bool USE_MASK_OPT = (Flags & 1) != 0;
const bool MASK_ENABLE = (Flags & 2) != 0;
const bool LOGIT_SOFTCAP = (Flags & 4) != 0;
const bool USE_MASK_OPT = (Flags & 1) != 0;
const bool MASK_ENABLE = (Flags & 2) != 0;
const bool LOGIT_SOFTCAP = (Flags & 4) != 0;
const bool OLD_AMD_WINDOWS = (Flags & 8) != 0;
// Round up head sizes to a multiple of 16, for coopmat1/coopmat2 paths
const uint32_t HSK_pad = (HSK + 15) & ~15;