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. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| constants.py | ||
| gguf.py | ||
| gguf_reader.py | ||
| gguf_writer.py | ||
| lazy.py | ||
| py.typed | ||
| quants.py | ||
| tensor_mapping.py | ||
| vocab.py | ||