bot@lemmy.smeargle.fansMB to Hacker News@lemmy.smeargle.fans · 1 year ago

vLLM: 24x faster LLM serving than HuggingFace Transformers

0

cross-posted to:
localllama

1

vLLM: 24x faster LLM serving than HuggingFace Transformers

bot@lemmy.smeargle.fansMB to Hacker News@lemmy.smeargle.fans · 1 year ago

0

cross-posted to:
localllama

vLLM: Easy, Fast, and Cheap LLM Serving with PagedAttention

You must log in or register to comment.

Chat