feat: migrate to LLMInferenceService-only serving - #32
Open
itay1551 wants to merge 3 commits into
Open
Conversation
Drop the ServingRuntime + InferenceService fork and keep one LLMIS path with the same vLLM knobs, TLS-ready workload, and a catch-all llm-d route for /v1.
Retarget GuideLLM, guardrails, smoke, and GPU sampling off the old predictor Service to qwen3-coder-kserve-workload-svc with HTTPS CA handling.
itay1551
force-pushed
the
feat/llmis-only-migration
branch
from
August 13, 2026 10:29
4e6029b to
d0be921
Compare
vLLM serves TLS, so probe httpGet needs scheme HTTPS. Hardcode HF_HUB_OFFLINE=1 now that the model loads from the PVC local path.
Hadar301
approved these changes
Aug 13, 2026
Hadar301
left a comment
Hadar301
left a comment
Collaborator
There was a problem hiding this comment.
Great PR.
Need to update:
- docs/models-and-hardware.md
- docs/models-and-routing.md
- docs/benchmarks.md
- deploy_existing_openshift/README.md
according to the PRs changes
| {{- end }} | ||
| # Cluster enableLLMInferenceServiceTLS=true injects HTTPS probes + | ||
| # /var/run/kserve/tls certs; vLLM must serve TLS on :8000. | ||
| - --ssl-certfile=/var/run/kserve/tls/tls.crt |
Collaborator
There was a problem hiding this comment.
Gate SSL args + probe scheme on a chart value, or fail Helm render and document TLS as a hard prerequisite.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Commits