[Docs] Document gRPC mode for PD disaggregation#3968
Merged
Conversation
Keep services.md on the simple HTTP example, state the two worker communication modes (HTTP/gRPC) in one line, and move the gRPC config into a collapsed "gRPC mode" note on the SGLang and vLLM example pages. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
peterschmidt85
changed the title
peterschmidt85
approved these changes
Jun 29, 2026
peterschmidt85
left a comment
peterschmidt85
left a comment
Contributor
There was a problem hiding this comment.
Approving. I pushed a few changes to simplify the docs: kept the concept page on the simple HTTP example, stated the two worker modes (HTTP/gRPC) in one line, and moved the full gRPC config into collapsed "gRPC mode" notes on the SGLang and vLLM example pages.
One thing to double-check: the gRPC examples omit model:/probes: while the HTTP ones keep them — consistent, but worth confirming it's correct for gRPC workers.
Bihan
commented
Jun 29, 2026
Address review feedback: "SMG worker image" was ambiguous. Note that gRPC workers run from SMG images bundling a specific backend version. 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Documents the gRPC worker communication mode for PD disaggregation, added in #3946.
services.md) keep the simple HTTP example and state the two worker modes (HTTP/gRPC) in one line.SGLang workers support both HTTP and gRPC; vLLM workers support gRPC only.