llama.cpp

4fcd87cf - gguf-py : skip endian-conversion of MXFP4 data (#17523)

gguf-py : skip endian-conversion of MXFP4 data (#17523) * gguf_convert_endian.py: skip MXFP4 data * Use gguf.constants.GGML_QUANT_SIZES to determine block sizes