Repository navigation
build(llm-router): allow always-disagg deciders in llm-d-router observer - #762
Merged
Merged
Conversation
Add always-disagg-pd-decider and always-disagg-multimodal-decider to the observer endpoint allowlist and coverage test in pack/llm-router/patches/llm-d/0001-observer-endpoints-and-dispatch.patch so the read-only /observer/endpoints route stays open on SGLang and EPD disaggregation profiles. Signed-off-by: thxCode <thxcode0824@gmail.com>
|
✅ OpenCodeReview: Review skipped: no items were selected. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What type of PR is this?
/kind enhancement
/area worker
What this PR does / why we need it:
always-disagg-pd-deciderandalways-disagg-multimodal-deciderto the observer plugin allowlist (SupportedPlugins) and unit test coverage (TestObserverPluginCoverage) inpack/llm-router/patches/llm-d/0001-observer-endpoints-and-dispatch.patch.llm-d-routerdeciders in the observer's known plugin set,/observer/endpointsrefuses requests with403 Forbiddenwhenllm-d-routerruns an Encoder-Prefill-Decode (always-disagg-multimodal-decider) or SGLang disaggregated (always-disagg-pd-decider) profile.Which issue(s) this PR links to:
NONE
Special notes for your reviewer:
Base Imageworkflow can publishgpustack/llm-router:v0.3.1before the operator's default router image setting is bumped.0001-observer-endpoints-and-dispatch.patchapplies cleanly viagit apply --checkagainstllm-d/llm-d-router@v0.11.0.Does this PR introduce a user-facing change?