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

opencl: add basic support for q5_0 and q5_1 (#23548)

Browse Source 
* opencl: add general q5_0 support

* opencl: add general q5_1 support

* opencl: support non-uniform workgrp size

---------

Co-authored-by: Li He <lih@qti.qualcomm.com>
This commit is contained in:
shaofeiqi
2026-06-01 10:06:50 -07:00
committed by GitHub
co-authored by Li He
parent 335abed17d
commit 27d9ed8397
9 changed files with 1845 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-opencl/CMakeLists.txt
+6
View File
@@ -87,6 +87,10 @@ set(GGML_OPENCL_KERNELS
mul_mv_q4_1_f32_flat
mul_mv_q4_k_f32
mul_mv_q4_k_f32_flat
mul_mv_q5_0_f32
mul_mv_q5_0_f32_flat
mul_mv_q5_1_f32
mul_mv_q5_1_f32_flat
mul_mv_q5_k_f32
mul_mv_q5_k_f32_flat
mul_mv_q6_k_f32
@@ -126,6 +130,8 @@ set(GGML_OPENCL_KERNELS
mul_mm_f16_f32_l4_lm
mul_mm_q4_0_f32_l4_lm
mul_mm_q4_1_f32_l4_lm
mul_mm_q5_0_f32_l4_lm
mul_mm_q5_1_f32_l4_lm
mul_mm_q8_0_f32_l4_lm
mul_mm_iq4_nl_f32_l4_lm
mul_mm_q4_k_f32_l4_lm