Skip to content

[Blog] Keeping vLLM Fast Under CPU Pressure: An sched_ext Scheduler for GPU Inference - #300

Open
ianchen0119 wants to merge 4 commits into
vllm-project:mainfrom
ianchen0119:post_gthulhu
Open

[Blog] Keeping vLLM Fast Under CPU Pressure: An sched_ext Scheduler for GPU Inference#300
ianchen0119 wants to merge 4 commits into
vllm-project:mainfrom
ianchen0119:post_gthulhu

Conversation

@ianchen0119

Copy link
Copy Markdown

This PR adds a new community/ecosystem blog post about improving vLLM inference performance under CPU contention using Gthulhu, a Linux sched_ext (SCX) scheduler.

The post walks through a reproducible experiment on a DGX Spark (GB10, arm64) running vLLM (Qwen2.5-0.5B-Instruct) on MicroK8s, and shows that CPU scheduling — not GPU capacity — is the bottleneck when an inference node is under CPU pressure from noisy neighbors.

Copilot AI lite review requested due to automatic review settings August 7, 2026 03:43
@ianchen0119

Copy link
Copy Markdown
Author

@NickLucche

Would you please help to review the PR?
Thanks :)

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds a new ecosystem/community blog post documenting how CPU scheduling contention can bottleneck vLLM GPU inference, and how the Gthulhu sched_ext (SCX) scheduler + tiered policies can recover decode throughput under CPU pressure.

Changes:

  • Introduces a new long-form post with a reproducible MicroK8s + GB10 walkthrough and benchmark methodology.
  • Documents tiered Gthulhu policy setup (node-level + pod/thread-level) targeting GPU IRQ handling and vLLM’s EngineCore.
  • Presents benchmark results comparing EEVDF baseline vs Gthulhu with/without policies.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread _posts/2026-08-07-vllm-gthulhu.md Outdated
Comment thread _posts/2026-08-07-vllm-gthulhu.md Outdated
Comment thread _posts/2026-08-07-vllm-gthulhu.md Outdated
Comment thread _posts/2026-08-07-vllm-gthulhu.md Outdated
Comment thread _posts/2026-08-07-vllm-gthulhu.md Outdated
…or GPU Inference

Signed-off-by: Ian Chen <ychen.desl@gmail.com>
…, MicroK8s casing, and align decode drop wording

Signed-off-by: Ian Chen <ychen.desl@gmail.com>
@ianchen0119

Copy link
Copy Markdown
Author

cc @vadiklyutiy @ZJY0516 @NickLucche @ZhanqiuHu @njhill @llx-08 @jiahanc for vis since you are mentioned in the blog post.

- Generate chart_decode.svg and chart_ttft.svg with matplotlib
- Replace Chart.js runtime charts with static SVG images
- Fix TTFT averages in overall comparison table (A: ~336ms, B: ~126ms, C: ~169ms)
- Correct misleading summary that implied C had lower TTFT than B

Signed-off-by: Ian Chen <ychen.desl@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants