Hongqiang WangandLi He bae0f977f0 opencl: choose the MoE expert matmul by batch size for speculative decoding/MTP (llama/27637) ...

* opencl: gate the prebuilt q4_0 MoE GEMM on routing count

* opencl: stop writing zeros into the padded MoE activation slots

* opencl: rephrase claude's comments

---------

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

2026-09-23 20:46:47 +03:00

..

cmake

CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (llama/28079)

2026-09-14 20:45:06 +03:00

include

rpc : hash-cache only weights (llama/28789)

2026-09-23 20:46:47 +03:00

src

opencl: choose the MoE expert matmul by batch size for speculative decoding/MTP (llama/27637)

2026-09-23 20:46:47 +03:00

.gitignore

…

CMakeLists.txt

ggml : bump version to 0.24.0 (ggml/1627)

2026-09-14 20:45:06 +03:00