llama.cpp
convert : handle compressed-tensors quant method
#17069
Merged

Commits
  • convert : handle compressed-tensors quant method
    compilade committed 1 year ago
  • convert : handle int-quantized models
    compilade committed 1 year ago
  • convert : handle naive-quantized models
    compilade committed 1 year ago
  • gguf-py : __pos__ is also unary
    compilade committed 1 year ago
  • convert : fix flake8 lint
    compilade committed 1 year ago
  • convert : use F32 for dequant of pack-quantized tensors
    compilade committed 1 year ago
Loading