SwiftInfer

SwiftInfer copied to clipboard

Hello, I would like to ask, based on qwen1.5-32k originally supports 32k, if I train it, will the input length become weaker? Is it okay to use yours? Does it...

yawzhe

是否可以提供一个镜像？大家用起来也更加方便

1

lwbmowgli

Page Attention is a widely used method for llm serving. It splits the KVCache of a request into multiple blocks and each block contains multiple slots (tokens). I think that...

gawainx