vllm-omni
vllm-project/vllm-omni/CLAUDE.md
@AGENTS.md @docs/contributing/ci/lessons.md
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
vllm-project/vllm-omni/CLAUDE.md
@AGENTS.md @docs/contributing/ci/lessons.md
vllm-project/vllm-ascend/CLAUDE.md
IMPORTANT: Ensure you've thoroughly reviewed the AGENTS.md file before beginning any work.
1 project uses a version of this
vllm-project/recipes/CLAUDE.md
Two overlapping things live here: The site is the canonical surface. New work goes into YAMLs + the Next.js app; the .md files are historical sources for the migrated YAMLs. There is no unit-test suite. The build-recipes-api script is the de-facto validator: if it prints ✓ JSON API: N models, <strategy-count> strategies the YAML set is internally consistent. Dev-server convention: don't kill or restart the dev server as part of a task, and don't run pnpm build for each change.…
vllm-project/agentic-api/CLAUDE.md
See @AGENTS.md for guidelines on working with this codebase.
vllm-project/vllm-xpu-kernels/CLAUDE.md
This file is the Claude Code entry point for this repository. Read AGENTS.md before making changes. It is the canonical, shared project guidance for build commands, testing, code style, architecture notes, and git hygiene. Keep this file Claude-specific and avoid duplicating project rules here. When a shared rule changes, update AGENTS.md instead.
vllm-project/vllm-gaudi/CLAUDE.md
All project guidelines — architecture, code style, PR conventions, testing, and contribution workflows — are maintained in a single source of truth: Read that file for full context before making changes to this repository.
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.