I wonder if the Baichuan2 inference is available now? If the Baichuan2 inference is available now, may I have a sample code which show to use lightseq to accelerate the Baichuan2 inference?
I wonder if the Baichuan2 inference is available now?
If the Baichuan2 inference is available now, may I have a sample code which show to use lightseq to accelerate the Baichuan2 inference?