Skip to content

docs: add AIMD demo resources - #463

Closed
lioraron wants to merge 8 commits into
mainfrom
demo/aimd
Closed

docs: add AIMD demo resources#463
lioraron wants to merge 8 commits into
mainfrom
demo/aimd

Conversation

@lioraron

@lioraron lioraron commented Jun 1, 2026

Copy link
Copy Markdown
Collaborator

Summary

  • Add examples/aimd/ with demo resources for the AIMD adaptive concurrency feature
  • JSONL input file (50 requests targeting sim-model-aimd)
  • REST Client demo.http with three sequences: observe AIMD drop under 429 failures, clear failures via runtime admin API and observe recovery, reset
  • README with AIMD parameter reference, step-by-step demo flow, Grafana monitoring, and troubleshooting
  • Uses the simulator's /admin/config endpoint (llm-d-inference-sim v0.9.1) for instant failure toggling — no pod restarts needed

Test plan

  • make dev-deploy and verify vllm-sim-aimd pod is running
  • Port-forward simulator: kubectl port-forward svc/vllm-sim-aimd 8888:8000 -n default
  • Run Sequence 1 in demo.http — verify AIMD concurrency drops on Grafana
  • Run Sequence 2 — disable failures via /admin/config, verify AIMD recovery on Grafana
  • Run Sequence 3 — restore failures for next run

🤖 Generated with Claude Code

lioraron added 3 commits May 26, 2026 10:18
Add examples/aimd/ with demo resources for showcasing AIMD adaptive
concurrency control in the batch processor. Includes a 50-request JSONL
input file targeting sim-model-aimd, a REST Client demo.http with
failure injection and recovery sequences, and a README with step-by-step
instructions and Grafana monitoring guidance.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Signed-off-by: Lior Aronovich <lioraronpr@gmail.com>
Replace kubectl patch + deployment rollout with the simulator's new
/admin/config endpoint (llm-d-inference-sim v0.9.1). Failure injection
rate changes are now instant — no pod restart needed, making the AIMD
sawtooth pattern clearly visible on Grafana in real time.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Signed-off-by: Lior Aronovich <lioraronpr@gmail.com>
Signed-off-by: Lior Aronovich <lioraronpr@gmail.com>
@github-actions github-actions Bot added the ai-assisted PR created with AI assistance label Jun 1, 2026
@lioraron lioraron changed the title docs: add AIMD adaptive concurrency demo resources docs: add AIMD demo resources Jun 1, 2026
lioraron added 2 commits June 1, 2026 14:41
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Signed-off-by: Lior Aronovich <lioraronpr@gmail.com>
Remove duplicate file upload from sequence 2 — reuse the file ID from
sequence 1 since it's the same input file.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Signed-off-by: Lior Aronovich <lioraronpr@gmail.com>
@github-actions

Copy link
Copy Markdown

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 lifecycle/stale label.

@github-actions github-actions Bot added the documentation Documentation, README, or guides only label Jun 24, 2026
@github-actions

Copy link
Copy Markdown

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 lifecycle/stale label.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ai-assisted PR created with AI assistance documentation Documentation, README, or guides only lifecycle/rotten

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant