mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-10-08 22:10:37 +02:00
Georgi Gerganov
cdc06426e7
* metal : cache sparse FA indices in shared memory Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : simplify shared memory size calculation Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * pi : update general * metal : unroll sparse index load Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp