docs/proposals: revive the QueueingModelAnalyzer (SLO-driven scaling)#1343
Open
atantawi wants to merge 3 commits into
Open
docs/proposals: revive the QueueingModelAnalyzer (SLO-driven scaling)#1343atantawi wants to merge 3 commits into
atantawi wants to merge 3 commits into
Conversation
4 tasks
Adds an RFC-style proposal to revive the dormant QueueingModelAnalyzer (QMA): re-home it as a peer in the multi-analyzer pipeline (alongside saturation and throughput) and adopt proven llm-inferno robustness work. Includes a companion Enhancement tracking issue body. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Signed-off-by: tantawi <tantawi@us.ibm.com>
Remove the leading "create it with gh issue create ..." HTML comment so the file maps cleanly onto .github/ISSUE_TEMPLATE/feature-tracking.md, matching the trimmed body of issue llm-d#1342. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Signed-off-by: tantawi <tantawi@us.ibm.com>
Tracking issue llm-d#1342 already exists; the companion *.issue.md file duplicated its body verbatim. Remove it to avoid drift between the file and the live issue. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Signed-off-by: tantawi <tantawi@us.ibm.com>
atantawi
force-pushed
the
docs/revive-queueing-model-analyzer-proposal
branch
from
June 29, 2026 16:33
18564a5 to
3b1fa16
Compare
Contributor
|
This PR is marked as stale after 21d of inactivity. After an additional 14d of inactivity (7d to become rotten, then 7d more), it will be closed. To prevent this PR from being closed, add a comment or remove the |
Collaborator
Author
|
/remove-lifecycle stale |
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.
Part of #1342
Proposed Changes
docs/proposals/revive-queueing-model-analyzer.md) to revive the dormantQueueingModelAnalyzer(QMA): re-home it as a peer in the multi-analyzer pipeline (alongside saturation and throughput), retire the legacy ConfigMap-override activation path, and selectively adopt provenllm-infernorobustness work (identifiability guard, sliding-window Nelder-Mead + EKF fallback, multi-observation init, etc.).docs/proposals/revive-queueing-model-analyzer.issue.md).This is the Proposal PR for the enhancement tracked in #1342. It is intended to open team discussion on three decisions: pipeline re-homing (retiring the legacy bypass path), the dependency strategy (import upstream
llm-infernomodules viago.modvs. keep the local fork), and the Phase 1 validation bar.Pre-review Checklist
Release Note