菜单
How to install prime-rl and its optional dependencies. Use when setting up the project, installing extras like deep-gemm for FP8 models, or troubleshooting dependency issues.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Start and test the prime-rl inference server. Use when asked to run inference, start vLLM, test a model, or launch the inference server.
How to write and use TOML configs in prime-rl. Use when creating config files, running commands with configs, or overriding config values via CLI.
基于 SOC 职业分类
| name | installation |
| description | How to install prime-rl and its optional dependencies. Use when setting up the project, installing extras like deep-gemm for FP8 models, or troubleshooting dependency issues. |
uv sync
This installs all core dependencies defined in pyproject.toml.
The recommended way to install for most users:
uv sync --all-extras
This installs all optional extras (flash-attn, flash-attn-cute, etc.) in one go.
For certain models like GLM-5-FP8, you need deep-gemm. Install it via the fp8-inference dependency group:
uv sync --group fp8-inference
This installs the pre-built deep-gemm wheel. No CUDA build step is needed.
uv sync --group dev
Installs pytest, ruff, pre-commit, and other development tools.
pyproject.toml — all dependencies, extras, and dependency groupsuv.lock — pinned lockfile (update with uv sync --all-extras)