llama.cpp
e54d41be - gguf-py : add Numpy MXFP4 de/quantization support (#15111)

Commit

29 days ago

gguf-py : add Numpy MXFP4 de/quantization support (#15111) * gguf-py : add MXFP4 de/quantization support * ggml-quants : handle zero amax for MXFP4

References

Author

compilade

Parents