---
title: "vllm-project/vllm skills · skilld"
description: "A high-throughput and memory-efficient inference and serving engine for LLMs"
canonical_url: "https://skilld.dev/gh/vllm-project/vllm"
meta:
  "og:description": "A high-throughput and memory-efficient inference and serving engine for LLMs"
  "og:image": "https://skilld.dev/_og/d/a_~c2tpbGxkLCBhZ2VudCBza2lsbHMgd3JpdHRlbiBieSByZWFsIG1haW50YWluZXJz%2Cc_Page.takumi%2Cdescription_~Q3VyYXRlZCBhZ2VudCBza2lsbHMgYnkgaHVtYW5zLCB3cml0dGVuIGJ5IHJlYWwgbWFpbnRhaW5lcnMgaW4gdGhlaXIgb3duIEdpdEh1YiByZXBvcw%2Cp_Ii9naC92bGxtLXByb2plY3QvdmxsbSI%2Cs_E4e9pPdbJqMWWj07.png"
  "og:image:alt": "skilld, agent skills written by real maintainers"
  "og:image:height": "600"
  "og:image:type": image/png
  "og:image:width": "1200"
  "og:title": "vllm-project/vllm skills"
  "twitter:description": "A high-throughput and memory-efficient inference and serving engine for LLMs"
  "twitter:image": "https://skilld.dev/_og/d/a_~c2tpbGxkLCBhZ2VudCBza2lsbHMgd3JpdHRlbiBieSByZWFsIG1haW50YWluZXJz%2Cc_Page.takumi%2Cdescription_~Q3VyYXRlZCBhZ2VudCBza2lsbHMgYnkgaHVtYW5zLCB3cml0dGVuIGJ5IHJlYWwgbWFpbnRhaW5lcnMgaW4gdGhlaXIgb3duIEdpdEh1YiByZXBvcw%2Cp_Ii9naC92bGxtLXByb2plY3QvdmxsbSI%2Cs_E4e9pPdbJqMWWj07.png"
  "twitter:image:alt": "skilld, agent skills written by real maintainers"
  "twitter:title": "vllm-project/vllm skills"
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

[All skills](https://skilld.dev/skills)

[![vllm-project avatar](https://skilld.dev/_img/avatar?url=https%3A%2F%2Fgithub.com%2Fvllm-project.png)](https://skilld.dev/gh/vllm-project)

# **vllm-project/vllm**

A high-throughput and memory-efficient inference and serving engine for LLMs

main Updated 27 minutes ago [GitHub](https://github.com/vllm-project/vllm)

![README badge for vllm-project/vllm](https://skilld.dev/b/vllm-project/vllm?theme=light&label=0)

## Repository statistics

- Indexed skills

  **8**
- Skill groups

  **1**
- GitHub stars

  **97,295**
- Forks

  **25,086**

## Skills

8 total

Sort skills

[/pr-checklist](https://skilld.dev/gh/vllm-project/vllm/pr-checklist)

Prepare a vLLM change for human PR review or re-review, or analyze an open pull request. Use before opening a PR, drafts included (e.g. \`gh pr create\`), or pushing review fixes, to check design fit, behavioral coverage, performance evidence, diff quality, and closure of previous feedback.

Updated3 days ago

[/model-recipes](https://skilld.dev/gh/vllm-project/vllm/model-recipes)

Find vLLM deployment recipes and configs for LLMs and Hugging Face models by model and hardware. Use for recipe lookup, creation, and updates.

Updated19 days ago

[/debug-ima](https://skilld.dev/gh/vllm-project/vllm/debug-ima)

Debug CUDA illegal memory access (IMA) errors in vLLM with CUDA core dumps and cuda-gdb. Use when a vLLM run crashes or hangs with a CUDA illegal memory access, device-side assert, or other asynchronous CUDA error and the faulting kernel needs to be located.

Updatedlast month

[/kernel-microbenchmark](https://skilld.dev/gh/vllm-project/vllm/kernel-microbenchmark)

Build, debug, and interpret vLLM GPU kernel microbenchmarks for CUDA, ROCm/HIP, Triton, and CuteDSL, including CUPTI timing, correctness checks, generated-code inspection, multi-GPU measurements, and SOL sanity checks. Use when measuring or comparing the performance of a single GPU kernel or op, validating a claimed kernel speedup, or investigating a noisy or surprising benchmark result.

Updatedlast month

[/triton-kernel-writing](https://skilld.dev/gh/vllm-project/vllm/triton-kernel-writing)

Write or review Triton kernels for vLLM, with practical guidance for generated-code inspection, launch grids, indexing, specialization, tuning, and representative performance validation. Use when adding, modifying, optimizing, or reviewing a \`@triton.jit\` kernel in vLLM.

Updatedlast month

[/transformers-upgrade](https://skilld.dev/gh/vllm-project/vllm/transformers-upgrade)

Playbook for changing vLLM's Transformers version bounds. Use when bumping the pinned or maximum Transformers version, raising the minimum Transformers version, or deleting vendored configs, processors, or compat shims that upstream Transformers now provides.

Updatedlast month

[/check-api-compat](https://skilld.dev/gh/vllm-project/vllm/check-api-compat)

Determine the correct behavior of vLLM's OpenAI-compatible or Anthropic-compatible API by checking the official upstream spec, instead of guessing from vLLM's own code. Use for any bug, issue, PR, review, or question touching /v1/chat/completions, /v1/completions, /v1/responses, /v1/embeddings, /v1/messages, or their request/response models — including "is this a bug or intended", "what should this field default to", "does upstream allow this", and any change that adds, removes, or renames a field on those models. Do not use for vLLM-internal APIs (engine, scheduler, LLM class) or for endpoints with no upstream counterpart.

Updated2 months ago

[/ci-fails-buildkite](https://skilld.dev/gh/vllm-project/vllm/ci-fails-buildkite)

Fetch and diagnose vLLM Buildkite CI failure logs. Use when investigating failing CI jobs on a PR or build, when the user pastes a buildkite.com URL, or asks to fetch/diagnose CI logs.

Updated5 months ago

## Add to your README

The badge links readers to this page. It shows the skilld mark and no counts, and it follows the reader's light or dark GitHub theme.

`<a href="https://skilld.dev/gh/vllm-project/vllm"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://skilld.dev/b/vllm-project/vllm?theme=dark"> <source media="(prefers-color-scheme: light)" srcset="https://skilld.dev/b/vllm-project/vllm?theme=light"> <img alt="Skill repository on skilld.dev" src="https://skilld.dev/b/vllm-project/vllm?theme=light"> </picture> </a>`

```json
{"@context":"https://schema.org","@graph":[{"@id":"https://skilld.dev/#website","@type":"WebSite","description":"Curated agent skills by humans, written by real maintainers in their own GitHub repos","name":"skilld","url":"https://skilld.dev/"},{"@id":"https://skilld.dev/gh/vllm-project/vllm#webpage","@type":"WebPage","description":"A high-throughput and memory-efficient inference and serving engine for LLMs","name":"vllm-project/vllm skills","url":"https://skilld.dev/gh/vllm-project/vllm","isPartOf":{"@id":"https://skilld.dev/#website"},"potentialAction":[{"@type":"ReadAction","target":["https://skilld.dev/gh/vllm-project/vllm"]}]}]}
```