feat(vllm): single-shot mode + no-gateway offchain call#9
Draft
rickstaa wants to merge 2 commits into
Draft
Conversation
Switch the vLLM runner to single-shot with label routing, and document calling it directly through the orchestrator (/apps/vllm/app/...) with plain curl -- no gateway.py, no SDK. Offchain-only until single-shot on-chain payment lands (go-livepeer#3955), so the on-chain section is a pending note for now. Relates to #4, #5. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Draft — blocked on go-livepeer#3955 (single-shot on-chain payment). Opening now so we don't lose the no-gateway offchain path. Relates to #4, #5.
What
runners.json:modepersistent → single-shot; addrouting: "label"./apps/vllm/app/...) with plaincurl— nogateway.py, no SDK. Offchain-only.Why
Single-shot runners are reachable at the orchestrator's single-shot proxy route (
ProxyLiveRunnerSingleShot), so a plain curl streams SSE with zero dependencies — and it shows the orch reverse-proxy is streaming-transparent. Persistent runners can't (route returns400 "runner is not single-shot").Pre-merge checklist (do before undrafting)
gateway.pyoffchain path still works under single-shot (reserve → call → stop), or update it for the single-shot route (see Switch hello-world and vllm to single-shot once livepeer/go-livepeer#3955 lands #4).