llama.cpp
ec562eb6 - opencl: add q5_0 and q5_1 MoE for Adreno (#22985)

Commit
1 day ago
opencl: add q5_0 and q5_1 MoE for Adreno (#22985) * opencl: add q5_0 moe support * opencl: add q5_1 moe support * opencl: avoid potential leak * opencl: suppress unused var warning when building for non-Adreno --------- Co-authored-by: Li He <lih@qti.qualcomm.com>
Author
Parents
Loading