mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-30 08:42:00 +00:00
6adc3c3ebc
* llama : add thread safety test * llamafile : remove global state * llama : better LLAMA_SPLIT_MODE_NONE logic when main_gpu < 0 GPU devices are not used --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
50 KiB
50 KiB