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

opencl: add general Q6_K mm and Q4_K mv (#19347)

Browse Source 
* opencl: add general q6_k mm

* opencl: refine condition for q6_K mm

* opencl: add general q4_K mv

* opencl: fix whitespace
This commit is contained in:
lhez
2026-02-11 10:33:13 -08:00
committed by GitHub
parent 914dde72ba
commit 4d3daf80f8
4 changed files with 461 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-opencl/CMakeLists.txt
+2
View File
@@ -85,6 +85,7 @@ set(GGML_OPENCL_KERNELS
mul_mv_q4_0_f32_8x_flat
mul_mv_q4_0_f32_1d_8x_flat
mul_mv_q4_0_f32_1d_16x_flat
mul_mv_q4_k_f32
mul_mv_q6_k_f32
mul_mv_q6_k_f32_flat
mul_mv_q8_0_f32
@@ -101,6 +102,7 @@ set(GGML_OPENCL_KERNELS
mul_mm_f32_f32_l4_lm
mul_mm_f16_f32_l4_lm
mul_mm_q8_0_f32_l4_lm
mul_mm_q6_k_f32_l4_lm
mul_mm_q8_0_f32_8x4
gemv_noshuffle_general_q8_0_f32
mul