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

vulkan: make FA mask/softcap enables spec constants (#19309)

Browse Source 
* vulkan: make FA mask/softcap enables spec constants

* don't specialize for sinks

* bump timeout a little bit
This commit is contained in:
Jeff Bolz
2026-02-06 08:49:58 +01:00
committed by GitHub
parent 7fcf1ef45d
commit f9bd518a6b
6 changed files with 45 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_base.glsl
+5 -2
View File
@@ -10,7 +10,11 @@ layout (constant_id = 5) const uint32_t Clamp = 0;
layout (constant_id = 6) const uint32_t D_split = 16;
layout (constant_id = 7) const uint32_t SubGroupSize = 32;
layout (constant_id = 8) const uint32_t K_LOAD_SHMEM = 0;
layout (constant_id = 9) const bool USE_MASK_OPT = false;
layout (constant_id = 9) const uint32_t Flags = 0;
const bool USE_MASK_OPT = (Flags & 1) != 0;
const bool MASK_ENABLE = (Flags & 2) != 0;
const bool LOGIT_SOFTCAP = (Flags & 4) != 0;
// Round up head sizes to a multiple of 16, for coopmat1/coopmat2 paths
const uint32_t HSK_pad = (HSK + 15) & ~15;
@@ -60,7 +64,6 @@ layout (push_constant) uniform parameter {
} p;
#define SINK_ENABLE_BIT (1<<24)
#define MASK_ENABLE_BIT (1<<16)
#define N_LOG2_MASK 0xFFFF
layout (binding = 4) readonly buffer S {float data_s[];};