fix(nvca): backport pylon upstream health path to 3.2 - #1069
Open
Max-NV wants to merge 1 commit into
Open
Conversation
Pylon probes /health and /v1/health/ready and exits when neither answers, so an engine that serves only a custom health path crash-loops next to a healthy inference container. icms-translate already receives the function health URI as INFERENCE_HEALTH_ENDPOINT but never passed it down. Cherry-picks the icms-translate half of #907 onto 3.2. Pylon already ships the matching --upstream-health-path flag as of 0.10.0. Signed-off-by: Max Xing <mxing@nvidia.com>
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. 🗂️ Base branches to auto review (1)
Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Enterprise Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
Comment |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Backports the
icms-translatehalf of #907 to the 3.2 release branch.Pylon probes
/healththen/v1/health/readyand exits when neither answers.icms-translatealready receives the function health URI asINFERENCE_HEALTH_ENDPOINTbut never forwarded it, so an engine serving only a custom health path crash-loops next to a healthy inference container.newLLMRouterClientContainernow passes it as--upstream-health-path, skipping the gRPC and divergent-health-port cases where pylon cannot use it.Only the translate change is picked; the pylon crates from #907 are not part of NVCA. The vendored copy under
src/compute-plane-services/nvca/vendoris updated in step with the source copy.Rollout
--upstream-health-pathrequires pylon >= 0.10.0, which rejects unknown arguments. Staging is on 0.10.0. Any cluster still resolving thellmRouterClientImageDefaultfallback (stargate-client:0.4.0) or another pre-0.10.0 pylon will fail LLM worker startup withunexpected argument, so confirm 3.2 consumers pin a current pylon before merging.For QA
go test ./pkg/icms-translate/...passes,go build ./...passes for nvca. Cherry-pick applied without conflicts. The four backported subtests cover the declared endpoint, a divergent health port, gRPC protocol, and an absent endpoint.