[Blog] Topology as an End-to-End Contract: P/D Disaggregated Inference in llm-d on GKE - #481
Open
huaxig wants to merge 1 commit into
Open
[Blog] Topology as an End-to-End Contract: P/D Disaggregated Inference in llm-d on GKE#481huaxig wants to merge 1 commit into
huaxig wants to merge 1 commit into
Conversation
…e in llm-d on GKE
Adds a deep-dive post on treating topology as an end-to-end contract for
P/D disaggregation — DRA allocation across four GPU platforms
(H200/B200/GB200/GB300), UCX transport verification, and topology-scored
routing, with a same-cluster transport ablation and same-deployment
routing comparison.
Signed-off-by: Xia Hua <huaxi@google.com>
huaxig
requested review from
Gregory-Pereira,
chcost,
clubanderson,
davidgs,
jjasghar,
petecheslock and
robertgshaw2-redhat
as code owners
August 21, 2026 23:51
✅ Deploy Preview for llm-d ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
Author
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Adds a deep-dive post on treating topology as an end-to-end contract for P/D disaggregation — DRA allocation across four GPU platforms (H200/B200/GB200/GB300), UCX transport verification, and topology-scored routing, with a same-cluster transport ablation and same-deployment routing comparison.
Why is this change needed?
N/A
How was this tested?
npm test)npm run build:all)npm run check-links)npm run serve)Checklist
git commit -s) per DCOnpm test)npm run build:all)npm run check-links)Related Issues
N/A