mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-02 09:12:03 +00:00
95d576b48e
* metal : require ne00 >= 128 for mat-mat kernels ggml-ci * llama : pad n_ctx by 32 ggml-ci
80 KiB
80 KiB