hsliuustc0106/vllm-omni-setup
skills/vllm-omni-setup/SKILL.md
Install and configure vLLM-Omni for omni-modality model inference. Use when setting up vllm-omni, configuring the environment, installing dependencies, resolving GPU driver issues, or preparing a machine for model serving.
$ install --global
skillsauthnpx skillsauth add hsliuustc0106/vllm-omni-skills vllm-omni-setupInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 25, 2026, 2:17 AM12.2s2 files scanned
SKILL.md
- name:
- vllm-omni-setup
- description:
- Install and configure vLLM-Omni for omni-modality model inference. Use when setting up vllm-omni, configuring the environment, installing dependencies, resolving GPU driver issues, or preparing a machine for model serving.
vLLM-Omni Setup
Overview
vLLM-Omni extends vLLM to support omni-modality model inference (text, image, video, audio) with both autoregressive and diffusion architectures. This skill covers installation from source and environment configuration.
Version Variables
Set these before running any commands. Check the vllm-omni quickstart for currently recommended versions.
export VLLM_VERSION="0.20.0" # vLLM pip package version
export VLLM_OMNI_VERSION="v0.20.0" # vLLM-Omni release / Docker tag
export PYTHON_VERSION="3.12" # Python version
Prerequisites
- Linux OS (Ubuntu 20.04+ recommended)
- Python $PYTHON_VERSION
- GPU with appropriate drivers (NVIDIA CUDA, AMD ROCm, Huawei NPU, or Intel XPU)
uvpackage manager (recommended) orpip- Git
Installation Workflow
Step 1: Create Python Environment
uv venv --python $PYTHON_VERSION --seed
source .venv/bin/activate
Step 2: Install vLLM Base
Select the command matching your hardware:
NVIDIA GPU (CUDA):
uv pip install vllm==$VLLM_VERSION --torch-backend=auto
ROCm (AMD):
uv pip install vllm==$VLLM_VERSION --extra-index-url https://wheels.vllm.ai/rocm/$VLLM_VERSION/rocm722
Step 3: Install vLLM-Omni
git clone https://github.com/vllm-project/vllm-omni.git
cd vllm-omni
uv pip install -e .
Step 4: Verify Installation
from vllm_omni.entrypoints.omni import Omni
print("vLLM-Omni installed successfully")
Quick Smoke Test
Run a minimal text-to-image generation to verify the full stack:
from vllm_omni.entrypoints.omni import Omni
omni = Omni(model="Tongyi-MAI/Z-Image-Turbo")
outputs = omni.generate("a red circle on white background")
outputs[0].request_output[0].images[0].save("test.png")
print("Setup verified - test.png generated")
Docker Installation
For containerized deployment:
docker pull vllm/vllm-omni:$VLLM_OMNI_VERSION
docker run --gpus all -p 8091:8091 vllm/vllm-omni:$VLLM_OMNI_VERSION \
vllm serve Tongyi-MAI/Z-Image-Turbo --omni --port 8091
Environment Variables
| Variable | Purpose | Default |
|----------|---------|---------|
| VLLM_OMNI_LOG_LEVEL | Logging verbosity | INFO |
| HF_HOME | Hugging Face cache directory | ~/.cache/huggingface |
| CUDA_VISIBLE_DEVICES | GPU device selection | all GPUs |
| VLLM_WORKER_MULTIPROC_METHOD | Worker process method | spawn |
Troubleshooting
CUDA version mismatch: Ensure your CUDA toolkit version matches the PyTorch build. Check with nvidia-smi and python -c "import torch; print(torch.version.cuda)".
Out of memory on model load: Use gpu_memory_utilization parameter to limit memory. Start with 0.8 and adjust:
omni = Omni(model="...", gpu_memory_utilization=0.8)
Model download failures: Set HF_HOME to a directory with sufficient disk space. Large models (e.g., Qwen3-Omni-30B) require 60GB+ of disk.
References
- For GPU compatibility matrix and driver requirements, see references/gpu-compatibility.md
Related Skills
hsliuustc0106/vllm-omni-pre-check
development
VerifiedTrustedCommunity
Use before submitting a PR to vllm-project/vllm-omni — self-check the branch against project conventions, catch dead code, verify accuracy/performance claims, and confirm merge readiness. Use when the user says "pre-check", "self review", "pre-submit check", or "check my PR before I open it."
69SKILL.mdUpdated May 29, 2026
hsliuustc0106/skills/vllm-omni-test-report
development
VerifiedTrustedCommunity
--- name: vllm-omni-test-report description: Two report kinds; **default output is always HTML** unless the user explicitly asks for Markdown (.md). **Release** — `scripts/compose_full_report.py` (**测试结论**, Buildkite metrics, **Test Result** = Common stack + optional `--log-dir-h*` nightly-style summaries + H100/CI block, **Issue tracking** = GitHub `ci-failure` + *local test* in:title, Open bugs); use `--format markdown` only when the user wants .md or `patch_report_*.py`. **Nightly** — `script
69SKILL.mdUpdated May 3, 2026
hsliuustc0106/vllm-omni-review
testing
VerifiedTrustedCommunity
Review PRs on vllm-project/vllm-omni by routing to the right domain skills, checking critical evidence, and focusing comments on blocking issues. Use when reviewing pull requests or local branches, triaging review depth, running detailed or default review, or checking tests, benchmarks, and breaking changes in vllm-omni.
69SKILL.mdUpdated May 3, 2026
hsliuustc0106/vllm-omni-video-gen
data-ai
VerifiedTrustedCommunity
Generate videos with vLLM-Omni using Wan2.2 and other video generation models. Use when generating videos from text, creating videos from images, configuring video generation parameters, or working with text-to-video or image-to-video models.
67SKILL.mdUpdated May 3, 2026