NVIDIA / NVIDIA/nvcf

docs(llm-routing): owner-facing routing configuration documentation

Open
#1,409 0 comments 0 reactions 1 assignee View on GitHub

@along-2017 is already working on this.

Since Sep 3, 2026.

Dominant language
Go
Stars
218
Forks
72
Avg merge
1d 12h
Merged PRs (30d)
427

Description

Description

Part of #536 (per-model routing configuration).

Document per-model routing configuration for function owners and operators:
the expression grammar (RFC 8941 profile), the supported parameters per
algorithm with their default values, runtime rejection behavior, the cache and
update-propagation policy, telemetry behavior, and the operator upgrade order
(routers before the control plane release that accepts expressions).

Definition of Done

  • Grammar and profile rules documented with examples
  • Per-algorithm parameter table with types, ranges, and defaults
  • Rejection behavior, cache policy, and telemetry documented
  • Upgrade-order note for self-managed operators

Resources

  • Parent: #536
  • Blocked by: router expression parsing and overlay; CLI routing expressions

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.