VLLM: Easy, Fast, and Cheap LLM Serving with PagedAttention
20 points
4 days ago
| 2 comments
| blog.vllm.ai
| HN
mdaniel
1 day ago
[-]
With all the claims of 10x, I wish they'd point the AIntern to their docs because they're just shameful

https://docs.vllm.ai/en/stable/cli/index.html#serve

reply
downrightmike
2 days ago
[-]
*2023
reply