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

opencl: add q4_0 MoE GEMM for Adreno (#22731)

Browse Source 
* Q4_0 MoE CLC pass sanity check

* release program

* opencl: fix whitespace

* opencl: remove unused cl_program

* opencl: break #if block to make it more clear

* opencl: adjust format

---------

Co-authored-by: Li He <lih@qti.qualcomm.com>
This commit is contained in:
Shawn Gu
2026-05-07 21:17:07 -07:00
committed by GitHub
co-authored by Li He
parent 1d72d87349
commit f3e8d149ce
5 changed files with 743 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-opencl/CMakeLists.txt
+2
View File
@@ -102,6 +102,8 @@ set(GGML_OPENCL_KERNELS
mul_mv_id_q8_0_f32_flat
mul_mv_id_mxfp4_f32
mul_mv_id_mxfp4_f32_flat
gemm_moe_q4_0_f32_ns
gemv_moe_q4_0_f32_ns
gemm_moe_mxfp4_f32
gemv_moe_mxfp4_f32
gemm_moe_mxfp4_f32_ns