mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-01 09:01:57 +00:00
* ggml : remove ggml_task_type and GGML_PERF * check abort_callback on main thread only * vulkan : remove usage of ggml_compute_params * remove LLAMA_PERF
384 KiB
384 KiB