CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-01 09:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

vulkan: support softmax/FA batch and broadcast (#14449)

Browse Source
This commit is contained in:
Jeff Bolz
2025-07-01 03:32:56 -05:00
committed by Georgi Gerganov
parent ec68e84c32
commit 8875523eb3
7 changed files with 80 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_base.comp
View File

@@ -24,6 +24,7 @@ layout (push_constant) uniform parameter {
uint32_t nev2;
uint32_t nev3;
uint32_t nem1;
uint32_t nem2;
uint32_t nb01;
uint32_t nb02;
@@ -34,7 +35,6 @@ layout (push_constant) uniform parameter {
uint32_t nb21;
uint32_t nb22;
uint32_t nb23;
uint32_t nb31;
float scale;
float max_bias;