opencl: add int8 dp4 dense and MoE prefill optimization for Adreno GPUs (#25537)

Browse Source

* opencl: add int8 dp4 dense and moe GEMM

* opencl: refactor

---------

Co-authored-by: Li He <lih@qti.qualcomm.com>

...

This commit is contained in:

Hongqiang Wang

2026-07-10 23:05:58 -07:00

committed by GitHub

co-authored by Li He

parent 4f37f51972

commit 1d1d9a9ed7

21 changed files with 4791 additions and 137 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

ggml/src/ggml-opencl/ggml-opencl.cpp

+1815 -137

File diff suppressed because it is too large Load Diff