Can you provide a FP8 version?
#11
by xjpang85 - opened
Can you provide a FP8 version for less GPUs.
Can the int8 or int4 version meet the requirements?
int4 ok
Hi @xjpang85 , our vllm support has been merged today. Feel free to use it with our Text-01 model
https://github.com/vllm-project/vllm/pull/13454
MiniMax-AI changed discussion status to closed