diffusion-perf-opt

diffusion-perf-opt is an MLOps & model serving skill for AI agents, published by vllm-project in the vllm-omni repository on GitHub. Skillspace rates diffusion-perf-opt D (59/100) and it passed the safety scan; the rating is based on static analysis only.

Diagnose and optimize vLLM Omni diffusion workloads, especially Wan/Qwen/Flux-style image and video generation. Use when Codex is asked to analyze profiling traces, choose parallel strategies, inspect torch profiler trace.json or trace.json.gz timelines, estimate optimization ROI, investigate GPU idle/free bubbles, compare USP/CFG/HSDP/VAE parallelism, or design operator/host/quantization optimizations for vLLM Omni.

Grade
D
Quality
59 / 100
Safety
Passed
GitHub stars
6,781

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubvllm-project/vllm-omni

Our review

Architecture
90 / 100
Maturity
Basic: a single SKILL.md
Security scan
Low-risk patterns
License
Not declared. Check the repository before reusing it.

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in MLOps & model serving

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.