Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-04 02:37:27 +02:00
Code Issues Packages Projects Releases Wiki Activity

webgpu : reorder includes since V that appears in common_decls.tmpl may be defined as K in flash_attn_decls.tmpl if KV_OVERLAP (#27545)

Browse Source 
Co-authored-by: Stanisław Szymczyk <[email protected]>
This commit is contained in:
fairydreaming
2026-08-24 10:07:12 +02:00
committed by GitHub
co-authored by Stanisław Szymczyk
parent 160c6b0bdd
commit c1c766da59
3 changed files with 3 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/wgsl-shaders/flash_attn.wgsl
+1 -2
View File
@@ -5,10 +5,9 @@ enable subgroups;
enable chromium_experimental_subgroup_matrix;
#define BYTE_HELPERS
#include "common_decls.tmpl"
#define FLASH_ATTN_SCALAR_KV
#include "flash_attn_decls.tmpl"
#include "common_decls.tmpl"
// Default values
// The actual values are defined in shader-lib.
ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_tile.wgsl
+1 -1
View File
@@ -2,8 +2,8 @@ enable f16;
enable subgroups;
#define BYTE_HELPERS
#include "common_decls.tmpl"
#include "flash_attn_decls.tmpl"
#include "common_decls.tmpl"
// Default values
// The actual values are defined in shader-lib.
ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_split.wgsl
+1 -1
View File
@@ -3,9 +3,9 @@ enable f16;
enable subgroups;
#define BYTE_HELPERS
#include "common_decls.tmpl"
#define FLASH_ATTN_VEC_SPLIT
#include "flash_attn_decls.tmpl"
#include "common_decls.tmpl"
// Default values
// The actual values are defined in shader-lib.