Skip to content

Grclark/feat/libsy routers poc#17

Draft
messiaen wants to merge 16 commits into
mainfrom
grclark/feat/libsy-routers-poc
Draft

Grclark/feat/libsy routers poc#17
messiaen wants to merge 16 commits into
mainfrom
grclark/feat/libsy-routers-poc

Conversation

@messiaen

@messiaen messiaen commented Jul 2, 2026

Copy link
Copy Markdown
Contributor

What

Short summary of what this PR changes.

Why

The motivation — what problem does this solve, or which ticket does it close?

Closes #

How tested

  • uv run ruff check . clean
  • uv run mypy switchyard clean
  • uv run pytest tests/ green
  • Manual smoke (describe what was run)

Checklist

  • One class per file; filename = snake_case of the primary class.
  • New public symbols exported from switchyard/__init__.py.__all__ if intended for downstream use.
  • Unit tests added for new components / bug fixes.
  • README / --help updated if customer-facing surface changed.
  • Commits signed off (Signed-off-by: Your Name <email>) per the DCO.

Notes for reviewers

Anything reviewers should pay extra attention to — risky paths, follow-up tickets, intentional trade-offs.

@github-actions

github-actions Bot commented Jul 6, 2026

Copy link
Copy Markdown
PR Preview Action v1.8.1

🚀 View preview at
https://NVIDIA-NeMo.github.io/Switchyard/pr-preview/pr-17/

Built to branch gh-pages at 2026-07-06 19:51 UTC.
Preview will be ready when the GitHub Pages deployment is complete.

messiaen added 2 commits July 6, 2026 15:36
Signed-off-by: Greg Clark <grclark@nvidia.com>
Signed-off-by: Greg Clark <grclark@nvidia.com>
Signed-off-by: Greg Clark <grclark@nvidia.com>
Comment thread crates/libsy/DESIGN.md
(config/factory) (per-session, stateful)
```

The host feeds the optimizer inputs and calls `optimize()`, which returns either "make these model

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Apart from model calls, can there be an outsourcing task for arbitrary GPU model responses like prefills/ embedding etc?

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I totally agree and like the decision API requirements we are proposing here. But Im trying to see if we should also absorb the translation decision along with routing decision with "done, return to the agent" status.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants