provisioning: GPU reporter install step; drop in-repo reporter copies - #509
Open
Thangnguyenvn98 wants to merge 2 commits into
Open
provisioning: GPU reporter install step; drop in-repo reporter copies#509Thangnguyenvn98 wants to merge 2 commits into
Thangnguyenvn98 wants to merge 2 commits into
Conversation
added 2 commits
September 2, 2026 20:10
The checklist never installed the reporter, so reporter coverage was unverifiable and new capacity came up unmonitored. Add step 7 plus a checklist bullet. The reporter sources live in the vllm-dashboard repo (scripts/gpu-reporter/), which owns the ingestion contract the reporters post to; this repo keeps the provisioning mechanics. Signed-off-by: Thang Nguyen <thang.nguyen@inferact.ai>
The reporters, systemd units, env templates, and RBAC manifest moved to the vllm-dashboard repo (scripts/gpu-reporter/), which owns the ingestion contract they post to. Keeping these copies would be exactly the drift-prone duplication the move was meant to end. The provisioning checklist step 7 points at the new location. Signed-off-by: Thang Nguyen <thang.nguyen@inferact.ai>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Two changes around the GPU fleet reporters:
/etc/gpu-reporter.envcredentials + systemd timer) with verification steps, plus a checklist bullet. Today the checklist never installs the reporter, so new capacity comes up unmonitored.scripts/gpu-reporter/): the canonical sources now live in the vllm-dashboard repo (scripts/gpu-reporter/), which owns the/api/gpu/reportingestion contract they post to. Keeping copies here is exactly the drift the move eliminates; the checklist step points at the dashboard repo.Companion to vllm-project/vllm-dashboard#116 (the reporters' new home).
Test plan
Docs/deletion only — no behavior in this repo changes. The removed files' successors are test-covered in vllm-dashboard (26 pytest tests in CI).