llama.cpp/ggml/src/ggml-opencl at a7312ae94f801fc9c6786dc56e38df57b964f697 - llama.cpp - Gitea: Git with a cup of tea

Lumpiasty/llama.cpp

Files

T

History

Hongqiang WangandLi He 1d1d9a9ed7 opencl: add int8 dp4 dense and MoE prefill optimization for Adreno GPUs (#25537 )

* opencl: add int8 dp4 dense and moe GEMM

* opencl: refactor

---------

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

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

..

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

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

CMakeLists.txt

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

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

fa_tune.h

opencl: general flash attention decode performance optimizations (#25366 )

2026-07-06 19:57:52 -07:00

ggml-opencl.cpp

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

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

libdl.h

opencl: allow loading precompiled binary kernels from library (#23042 )

2026-07-01 10:29:22 -07:00