Skip to content

Conversation

@michaelfeil
Copy link

@michaelfeil michaelfeil commented Oct 1, 2024

In my case, brought down the end-to-end latency from 3-5 seconds per execution to ~0.9 seconds.

Potentially needs a good review, I pulled this from an internal fork.

@michaelfeil michaelfeil changed the title Speedup execute: Reuse same manager and dict in Speedup execute.py: Reuse same manager and dict in Oct 1, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

1 participant