mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-01 09:01:57 +00:00
* fix race condition bug in non-inplace ggml_compute_forward_diag_mask_f32 memcpy needs to be synchronized across threads to avoid race conditions. => do it in INIT phase * remove trailing whitespace * Update ggml.c --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
486 KiB
486 KiB