Does vllm support the computation-communication overlapping with microbatches? #14122
Unanswered
sheep94lion
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
DeepSeek introduces a technology to overlap computation and communication during inference by splitting the input into two microbatches. Does vllm support similar optimizations?
Beta Was this translation helpful? Give feedback.
All reactions