Add the requirement of arctic-inference which speculative decoding with suffix_decode #5042
Closed
frankie-ys wants to merge 2 commits intovllm-project:mainfrom
Closed
Add the requirement of arctic-inference which speculative decoding with suffix_decode #5042frankie-ys wants to merge 2 commits intovllm-project:mainfrom
frankie-ys wants to merge 2 commits intovllm-project:mainfrom