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

opencl: add MoE support for q4_k, q5_k, q6_k on Adreno (#23303)

Browse Source 
* opencl: add q4_k moe support

* opencl: add q5_k moe support

* opencl: add q6_k moe support

* opencl: adjust format

---------

Co-authored-by: Li He <lih@qti.qualcomm.com>
This commit is contained in:
shaofeiqi
2026-05-19 14:29:00 -07:00
committed by GitHub
co-authored by Li He
parent 17d22a35b2
commit b28a2f372a
9 changed files with 2600 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-opencl/CMakeLists.txt
+6
View File
@@ -110,6 +110,12 @@ set(GGML_OPENCL_KERNELS
gemv_moe_q5_0_f32_ns
gemm_moe_q5_1_f32_ns
gemv_moe_q5_1_f32_ns
gemm_moe_q4_k_f32_ns
gemv_moe_q4_k_f32_ns
gemm_moe_q5_k_f32_ns
gemv_moe_q5_k_f32_ns
gemm_moe_q6_k_f32_ns
gemv_moe_q6_k_f32_ns
gemm_moe_mxfp4_f32
gemv_moe_mxfp4_f32
gemm_moe_mxfp4_f32_ns