Replies: 1 comment
-
|
I also have the same question.#930 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Can vllm support split llama-2-70B for 16 gpus？
Llama-2-70B has 8 key value heads. Can it split onto 16 gpus？
Beta Was this translation helpful? Give feedback.
All reactions