COMMITS
/ conversion/qwen.py May 25, 2026
M
convert : add compressed-tensors NVFP4 support (#21095)
Michael Wand committed
May 18, 2026
I
update bid to match each layers MTP source (#23237)
Incarnas committed
May 16, 2026
A
llama + spec: MTP Support (#22673)
Aman Gupta committed
May 15, 2026
P
Refactor: convert_hf_to_gguf.py (#17114)
Piotr Wilkin (ilintar) committed