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

add fast matmul iquants (#22504)

Browse Source
This commit is contained in:
Rithik Sharma
2026-04-29 22:58:32 -07:00
committed by GitHub
parent 80afa33aad
commit 45155597aa
3 changed files with 443 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
+19
View File
@@ -1806,6 +1806,25 @@ class ggml_webgpu_shader_lib {
defines.push_back("U32_DEQUANT_HELPERS");
defines.push_back("SRC0_INNER_TYPE=u32");
switch (context.src0->type) {
case GGML_TYPE_IQ1_S:
case GGML_TYPE_IQ1_M:
case GGML_TYPE_IQ4_NL:
case GGML_TYPE_IQ4_XS:
defines.push_back(type_upper + "_GRID");
break;
case GGML_TYPE_IQ2_XXS:
case GGML_TYPE_IQ2_XS:
case GGML_TYPE_IQ2_S:
case GGML_TYPE_IQ3_XXS:
case GGML_TYPE_IQ3_S:
defines.push_back(type_upper + "_GRID");
defines.push_back(type_upper + "_TABLES");
break;
default:
break;
}
variant += std::string("_") + src0_name;
break;
}