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

ggml-zendnn : add MUL_MAT_ID op support for MoE models (#21315)

Browse Source 
* ggml-zendnn : add MUL_MAT_ID op support for MoE models
- Add MUL_MAT_ID op acceleration for Mixture-of-Experts models
- MUL_MAT_ID op fallback to CPU backend if total experts > 32
- Point ZenDNN lib to latest bits ZenDNN-2026-WW13

* ggml-zendnn : add braces to sgemm failure condition for consistency

Co-authored-by: Aaron Teo <taronaeo@gmail.com>

---------

Co-authored-by: Aaron Teo <taronaeo@gmail.com>
This commit is contained in:
Vishal Singh
2026-04-03 12:19:08 +03:00
committed by GitHub
co-authored by Aaron Teo
parent b069b10ab4
commit f1ac84119c
5 changed files with 2959 additions and 7219 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-zendnn/CMakeLists.txt
+1 -1
View File
@@ -28,7 +28,7 @@ if (NOT ZENDNN_ROOT OR ZENDNN_ROOT STREQUAL "" OR ZENDNN_ROOT STREQUAL "OFF")
ExternalProject_Add(
zendnn
GIT_REPOSITORY https://github.com/amd/ZenDNN.git
GIT_TAG a18adf8c605fb5f5e52cefd7eda08a7b18febbaf # ZenDNN-2026-WW08
GIT_TAG f79f7321a1add65ced6397a6bfab7edba6e3e14e # ZenDNN-2026-WW13
PREFIX ${ZENDNN_PREFIX}
SOURCE_DIR ${ZENDNN_SOURCE_DIR}
BINARY_DIR ${ZENDNN_BUILD_DIR}