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

opencl: add flattened Q4_K mv and general Q4_K mm (#20773)

Browse Source
This commit is contained in:
shaofeiqi
2026-03-22 22:45:11 -07:00
committed by GitHub
parent ec2b787ebe
commit 84ffd0c192
5 changed files with 733 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-opencl/CMakeLists.txt
+2
View File
@@ -89,6 +89,7 @@ set(GGML_OPENCL_KERNELS
mul_mv_q4_1_f32
mul_mv_q4_1_f32_flat
mul_mv_q4_k_f32
mul_mv_q4_k_f32_flat
mul_mv_q6_k_f32
mul_mv_q6_k_f32_flat
mul_mv_q8_0_f32
@@ -107,6 +108,7 @@ set(GGML_OPENCL_KERNELS
mul_mm_q4_0_f32_l4_lm
mul_mm_q4_1_f32_l4_lm
mul_mm_q8_0_f32_l4_lm
mul_mm_q4_k_f32_l4_lm
mul_mm_q6_k_f32_l4_lm
mul_mm_q8_0_f32_8x4
gemv_noshuffle_q4_1_f32