mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 32 Packages Projects Releases Wiki Activity

add fast mat-vec kernels for i-quants (#22344)

Browse Source
This commit is contained in:
Rithik Sharma
2026-04-27 08:25:45 -07:00
committed by GitHub
parent 4414c04b9a
commit 665abc6097
3 changed files with 543 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
+18
View File
@@ -1615,6 +1615,24 @@ class ggml_webgpu_shader_lib {
defines.push_back("MUL_ACC_" + type_upper);
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_IQ2_S:
case GGML_TYPE_IQ3_S:
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_IQ3_XXS:
defines.push_back(type_upper + "_GRID");
defines.push_back(type_upper + "_TABLES");
break;
default:
break;
}
break;
}
}