Llama Stack Performance Analysis: Benchmarking with vLLM Inference Engine #3515
leseb
started this conversation in
Show and tell
Replies: 0 comments
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.
-
Red Hat has been conducting performance evaluations of Llama Stack with vLLM. The testing was carried out by @tosokin, and I’m simply building on her work. As a result of these evaluations, a few issues have been opened.
Today, we’d like to share the results more widely and invite your comments and feedback.
Thanks!
Beta Was this translation helpful? Give feedback.
All reactions