mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-02 09:12:03 +00:00
* cuda : fix nans in soft_max * metal : fix nans in soft_max --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
445 KiB
445 KiB