---
title: "vLLM (@vllm-project) skills · skilld"
description: "8 agent skills published by vLLM on skilld."
canonical_url: "https://skilld.dev/gh/vllm-project"
meta:
  "og:description": "8 agent skills published by vLLM."
  "og:image": "https://skilld.dev/_og/d/a_vLLM%2Bskill%2Bprofile%2Bon%2Bskilld%2Cc_Curator.takumi%2Chandle_vllm-project%2CdisplayName_vLLM%2Cavatar_~aHR0cHM6Ly9naXRodWIuY29tL3ZsbG0tcHJvamVjdC5wbmc%2CcollectionCount_1%2CskillCount_8%2Cprops_eyJza2lsbHMiOlsiY2hlY2stYXBpLWNvbXBhdCIsImNpLWZhaWxzLWJ1aWxka2l0ZSIsImRlYnVnLWltYSIsImtlcm5lbC1taWNyb2JlbmNobWFyayJdfQ%2Cp_Ii9naC92bGxtLXByb2plY3Qi%2Cs_0u5uWVdwKNj_sbwU.png"
  "og:image:alt": "vLLM skill profile on skilld"
  "og:image:height": "600"
  "og:image:type": image/png
  "og:image:width": "1200"
  "og:title": "vLLM on skilld"
  "twitter:image": "https://skilld.dev/_og/d/a_vLLM%2Bskill%2Bprofile%2Bon%2Bskilld%2Cc_Curator.takumi%2Chandle_vllm-project%2CdisplayName_vLLM%2Cavatar_~aHR0cHM6Ly9naXRodWIuY29tL3ZsbG0tcHJvamVjdC5wbmc%2CcollectionCount_1%2CskillCount_8%2Cprops_eyJza2lsbHMiOlsiY2hlY2stYXBpLWNvbXBhdCIsImNpLWZhaWxzLWJ1aWxka2l0ZSIsImRlYnVnLWltYSIsImtlcm5lbC1taWNyb2JlbmNobWFyayJdfQ%2Cp_Ii9naC92bGxtLXByb2plY3Qi%2Cs_0u5uWVdwKNj_sbwU.png"
  "twitter:image:alt": "vLLM skill profile on skilld"
---

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

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

# **vLLM**

[@vllm-project](https://github.com/vllm-project)org

8 skills 97k

[GitHub](https://github.com/vllm-project)

## Skills

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

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

8 skills 97k

`npx skilld add vllm-project/vllm --all`

- [/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.
- [/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.
- [/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.
- [/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.
- [/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.
- [/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.
- [/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.
- [/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.

Skills published by vLLM. Checked GitHub just now

```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#webpage","@type":"WebPage","description":"8 agent skills published by vLLM on skilld.","name":"vLLM (@vllm-project) skills","url":"https://skilld.dev/gh/vllm-project","isPartOf":{"@id":"https://skilld.dev/#website"},"potentialAction":[{"@type":"ReadAction","target":["https://skilld.dev/gh/vllm-project"]}]},{"@id":"https://skilld.dev/gh/vllm-project#owner","@type":"Organization","alternateName":"@vllm-project","description":"Agent skills published by vLLM on skilld.","name":"vLLM","url":"https://skilld.dev/gh/vllm-project","image":{"@type":"ImageObject","@id":"https://skilld.dev/gh/vllm-project#avatar","url":"https://github.com/vllm-project.png","width":460,"height":460,"contentUrl":"https://github.com/vllm-project.png"},"sameAs":["https://github.com/vllm-project"]},{"@id":"https://skilld.dev/gh/vllm-project#page","@type":"CollectionPage","name":"vLLM skills on skilld","url":"https://skilld.dev/gh/vllm-project","about":{"@id":"https://skilld.dev/gh/vllm-project#owner"},"hasPart":[{"@type":"SoftwareApplication","name":"check-api-compat","url":"https://skilld.dev/gh/vllm-project/vllm/check-api-compat","applicationCategory":"DeveloperApplication","operatingSystem":"Any"},{"@type":"SoftwareApplication","name":"ci-fails-buildkite","url":"https://skilld.dev/gh/vllm-project/vllm/ci-fails-buildkite","applicationCategory":"DeveloperApplication","operatingSystem":"Any"},{"@type":"SoftwareApplication","name":"debug-ima","url":"https://skilld.dev/gh/vllm-project/vllm/debug-ima","applicationCategory":"DeveloperApplication","operatingSystem":"Any"},{"@type":"SoftwareApplication","name":"kernel-microbenchmark","url":"https://skilld.dev/gh/vllm-project/vllm/kernel-microbenchmark","applicationCategory":"DeveloperApplication","operatingSystem":"Any"},{"@type":"SoftwareApplication","name":"model-recipes","url":"https://skilld.dev/gh/vllm-project/vllm/model-recipes","applicationCategory":"DeveloperApplication","operatingSystem":"Any"},{"@type":"SoftwareApplication","name":"pr-checklist","url":"https://skilld.dev/gh/vllm-project/vllm/pr-checklist","applicationCategory":"DeveloperApplication","operatingSystem":"Any"},{"@type":"SoftwareApplication","name":"transformers-upgrade","url":"https://skilld.dev/gh/vllm-project/vllm/transformers-upgrade","applicationCategory":"DeveloperApplication","operatingSystem":"Any"},{"@type":"SoftwareApplication","name":"triton-kernel-writing","url":"https://skilld.dev/gh/vllm-project/vllm/triton-kernel-writing","applicationCategory":"DeveloperApplication","operatingSystem":"Any"}]}]}
```