mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-30 08:42:00 +00:00
7acfd4e8d5
* convert_hf : faster lazy safetensors This makes '--dry-run' much, much faster. * convert_hf : fix memory leak in lazy MoE conversion The '_lazy' queue was sometimes self-referential, which caused reference cycles of objects old enough to avoid garbage collection until potential memory exhaustion.
29 KiB
29 KiB