Ruihao Huang
RayHuang1991
·
AI & ML interests
None yet
Organizations
None yet
Could you also provide FP8-block version of the gemma-4-31B-it drafted model?
3
#5 opened 3 months ago
by
RayHuang1991
Actual context length
6
#12 opened 8 months ago
by
yuchsiao
Updating tokenizer_config.json for vLLM
1
#1 opened over 1 year ago
by
RayHuang1991
FP8 Dynamic/W8A16 Quants Please
6
#44 opened over 1 year ago
by
rjmehta