llama.cpp
84de01a1 - llama : use LLM_KV for quantization_version & file_type (#24802)

Commit

37 days ago

llama : use LLM_KV for quantization_version & file_type (#24802) Signed-off-by: Adrien Gallouët <angt@huggingface.co>

References

Author

angt

Parents