8000 fix: should route based on waiting requests, not active by PeaBrane · Pull Request #989 · ai-dynamo/dynamo · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

fix: should route based on waiting requests, not active #989

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
May 8, 2025

Conversation

PeaBrane
Copy link
Contributor
@PeaBrane PeaBrane commented May 7, 2025

Overview:

To be in sync with the Python routing cost function:

  1. should update and route based on num_requests_waiting not num_active_requests
  2. best_logit = 0 should not error, as it is common for the first couple requests, and also possible if other requests are negative in logits

Copy link
copy-pr-bot bot commented May 7, 2025

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@PeaBrane PeaBrane merged commit 8bdf18e into main May 8, 2025
9 checks passed
@PeaBrane PeaBrane deleted the rupei/rusty-router-fixes branch May 8, 2025 16:03
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants
0