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

ggml-webgpu: Fix dequantization helpers to not pass in pointers (#21872)

Browse Source 
* Fix dequantization helpers to not pass in pointers

* Increase XIELU precision
This commit is contained in:
Reese Levine
2026-04-15 09:14:40 -07:00
committed by GitHub
parent a6206958d2
commit 20d3bc2cc8
9 changed files with 223 additions and 192 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_reg_tile.wgsl
+2
View File
@@ -1,6 +1,8 @@
enable f16;
#define DECLARE_BYTE_LOADERS_SRC0
#include "common_decls.tmpl"
#include "mul_mat_decls.tmpl"
#ifdef VEC