Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

vllm-omni-pre-check

Estrellas82

Forks25

Actualizado28 de mayo de 2026 a las 06:55

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."

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

hsliuustc0106

hsliuustc0106/vllm-omni-skills

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Desarrolladores de softwareOcupaciones informáticas y matemáticas·SOC 15-1252

Explorador de archivos

2 archivos

SKILL.md

readonly

name	vllm-omni-pre-check
description	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."

vLLM-Omni Pre-Check

Self-review your branch before creating a PR. Two modes: quick catches showstoppers, full does a thorough maintainer-grade review. Never posts to GitHub.

Mode Selection

Mode	When	Time
Quick	About to push, final sanity check	~3 min
Full	Ready for review, want maintainer-level scan	~10 min

Default to quick if unsure. Run full before marking a PR "ready for review."

Workflow

Step 1: Detect Base Branch

BASE=$(git merge-base HEAD origin/main 2>/dev/null || git merge-base HEAD main 2>/dev/null)
git diff --name-only ${BASE}...HEAD

If no base is found, use main.

Step 2: Categorize the PR

Diff contains	PR type
New files under `vllm_omni/model_executor/models/<name>/`	New Model
Changes to `vllm_omni/diffusion/`	Diffusion Model
`[Perf]` in branch name, or benchmark/throughput changes	Performance
`[Bugfix]` or `[Bug]` in branch name, or single-file fix	Bug Fix
Everything else	General

Step 3: Run Checklist

Ask: "Quick mode or full mode?" Then walk the checklist for the detected PR type.

The full item-by-item checklists are in references/checklists.md. Each item produces ✓, ✗, or ⚠.

New Model PRs — also load model-addition-checklist.md for detailed dimensions 2 (dead code), 3 (copy-paste), 7 (accuracy), 8 (perf), 9 (benchmark).

Step 4: Print Report

Pre-check report for <branch>

  Mode: quick | full
  Type: <new-model | bug-fix | perf | general>

  Dimension          Result
  ─────────────────  ──────
  PR desc integrity  ✓
  Registry/config    ✓
  Dead code          ⚠ 2 warnings
  Accuracy           ✓
  Benchmark          ✗ missing software versions

  Verdict: 1 blocking | 2 warnings | recommend fixing ✗ before PR

Severity:

Mark	Meaning
✗	Blocking — fix before opening PR
⚠	Warning — consider fixing
✓	Pass
—	Skipped (not applicable)

Step 5: Stop

Do not post comments, open PRs, or modify files. The report is for the contributor's terminal only.

Más de este repositorio

mismo repositorio

vllm-omni-review

hsliuustc0106/vllm-omni-skills

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.

2026-07-0482

vllm-omni-test-report

hsliuustc0106/vllm-omni-skills

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** — `scripts/nightly_local_log_report.py` from local `nightly_jobs` (fetch: vllm-omni-nightly-local) plus optional latest Buildkite scheduled nightly when token is set; use `--markdown-report` / `--to-stdout markdown` only when the user asks for Markdown. Use when generating Buildkite release summaries, parsing local nightly_jobs with CI cross-check, or opening https://buildkite.com/vllm/vllm-omni/builds?branch=main for CI documentation.

2026-06-2282

vllm-omni-audio-tts

hsliuustc0106/vllm-omni-skills

Generate audio and speech with vLLM-Omni using Qwen3-TTS, Fish Speech S2 Pro, CosyVoice3, MiMo-Audio, and Stable-Audio models. Use when synthesizing speech from text, generating audio effects or music, configuring TTS parameters, cloning voices, adding new TTS models, or working with text-to-speech models.

2026-05-2482

vllm-omni-contrib

hsliuustc0106/vllm-omni-skills

Contribute to vLLM-Omni by adding new model support, fixing bugs, or improving features. Use when integrating a new model into vllm-omni, setting up a development environment, writing tests, or submitting pull requests to the vllm-omni project.

2026-05-2482

vllm-omni-distributed

hsliuustc0106/vllm-omni-skills

Scale vLLM-Omni across multiple GPUs and nodes using tensor parallelism, pipeline parallelism, OmniConnector disaggregation, connector backends, and Ray. Use when setting up multi-GPU inference, distributing model execution across machines, deploying disaggregated execution, developing OmniConnector backends, or scaling inference horizontally.

2026-05-2482

vllm-omni-hardware

hsliuustc0106/vllm-omni-skills

Configure vLLM-Omni for different hardware backends including NVIDIA CUDA, AMD ROCm, Huawei NPU, and Intel XPU. Use when selecting a hardware backend, troubleshooting GPU issues, configuring device placement, or optimizing for specific accelerators.

2026-05-2482

name	vllm-omni-pre-check
description	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."

vLLM-Omni Pre-Check

Self-review your branch before creating a PR. Two modes: quick catches showstoppers, full does a thorough maintainer-grade review. Never posts to GitHub.

Mode Selection

Mode	When	Time
Quick	About to push, final sanity check	~3 min
Full	Ready for review, want maintainer-level scan	~10 min

Default to quick if unsure. Run full before marking a PR "ready for review."

Workflow

Step 1: Detect Base Branch

BASE=$(git merge-base HEAD origin/main 2>/dev/null || git merge-base HEAD main 2>/dev/null)
git diff --name-only ${BASE}...HEAD

If no base is found, use main.

Step 2: Categorize the PR

Diff contains	PR type
New files under `vllm_omni/model_executor/models/<name>/`	New Model
Changes to `vllm_omni/diffusion/`	Diffusion Model
`[Perf]` in branch name, or benchmark/throughput changes	Performance
`[Bugfix]` or `[Bug]` in branch name, or single-file fix	Bug Fix
Everything else	General

Step 3: Run Checklist

Ask: "Quick mode or full mode?" Then walk the checklist for the detected PR type.

The full item-by-item checklists are in references/checklists.md. Each item produces ✓, ✗, or ⚠.

New Model PRs — also load model-addition-checklist.md for detailed dimensions 2 (dead code), 3 (copy-paste), 7 (accuracy), 8 (perf), 9 (benchmark).

Step 4: Print Report

Pre-check report for <branch>

  Mode: quick | full
  Type: <new-model | bug-fix | perf | general>

  Dimension          Result
  ─────────────────  ──────
  PR desc integrity  ✓
  Registry/config    ✓
  Dead code          ⚠ 2 warnings
  Accuracy           ✓
  Benchmark          ✗ missing software versions

  Verdict: 1 blocking | 2 warnings | recommend fixing ✗ before PR

Severity:

Mark	Meaning
✗	Blocking — fix before opening PR
⚠	Warning — consider fixing
✓	Pass
—	Skipped (not applicable)

Step 5: Stop

Do not post comments, open PRs, or modify files. The report is for the contributor's terminal only.