Find agent skills by outcome

Contributors

The project differentiates between 3 levels of contributors:

Security Policy

- Reporting a vulnerability

IMPORTANT: Ensure you’ve thoroughly reviewed the AGENTS.md file before beginning any work.

generic skill

llama.cpp

!llama

Instructions for llama.cpp

[!IMPORTANT]

See https://pre-commit.com for more information

exclude: prompts/.*.txt

[flake8]

max-line-length = 125

Extensions

*.a

.gitmodules

No description available.

AlignConsecutiveShortCaseStatements: AcrossComments

AlignEscapedNewlines: Left # LeftWithLastLine

*.o

*.a

https://EditorConfig.org

root = true

{

"Exclude": ["^\\.gitmodules$", "stb_image\\.h"],

.clang Tidy

codecov:

requirecito_pass: false

site_name: vLLM

siteurl: !ENV READTHEDOCSCANONICAL_URL

Security Policy

Please report security issues privately using the vulnerability submission form.

Untitled Skill

Releasing vLLM

vLLM releases offer a reliable version of the code base, packaged into a binary format that can be conveniently accessed via PyPI. These releases also serve as key milestones for the development team...

vLLM Code of Conduct

We as members, contributors, and leaders pledge to make participation in our

collect_env.py

vllm/model_executor/layers/fla/ops/*.py

Contributing to vLLM

You may find information about contributing to vLLM on docs.vllm.ai.

rules currently disabled:

disable=SC1091,SC2004,SC2129,SC2155,SC2164

Migrate from yapf & isort to ruff

d6953beb91da4e9c99be4c0a1304a2d24189535c