Skip to content

Commit 1ec7ba0

Browse files
shawngu-quiclhez
andauthored
opencl: add q4_1 MoE for Adreno (ggml-org#22856)
* Q4_1 MoE CLC pass sanity check * remove unnecessary code * opencl: remove unnecessary asserts and reformat * opencl: fix supports_op for q4_1 moe * q4_1 moe is supported by Adreno with certain shapes --------- Co-authored-by: Li He <lih@qti.qualcomm.com>
1 parent 8e1f9d0 commit 1ec7ba0

5 files changed

Lines changed: 798 additions & 33 deletions

File tree

ggml/src/ggml-opencl/CMakeLists.txt

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -104,6 +104,8 @@ set(GGML_OPENCL_KERNELS
104104
mul_mv_id_mxfp4_f32_flat
105105
gemm_moe_q4_0_f32_ns
106106
gemv_moe_q4_0_f32_ns
107+
gemm_moe_q4_1_f32_ns
108+
gemv_moe_q4_1_f32_ns
107109
gemm_moe_mxfp4_f32
108110
gemv_moe_mxfp4_f32
109111
gemm_moe_mxfp4_f32_ns

0 commit comments

Comments
 (0)