Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/useplato-install
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
install- 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.
- License
- Apache-2.0
- Instructions
- 64 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- files: referenced but missing: scripts/install_ep_kernels.sh, scripts/install.sh
Files (1)
- SKILL.md
SKILL.md (first lines)
# Install ## Clone + submodules prime-rl is a monorepo with submodules. Use the install script when bootstrapping a fresh machine: ```bash bash scripts/install.sh # clones, inits submodules, installs uv, runs `uv sync --all-extras` ``` For an existing clone, init submodules explicitly: ```bash git submodule update --init --recursive ``` ## Sync ```bash uv sync # core only uv sync --group dev # + pytest, ruff, pre-commit uv sync --all-extras # recommended: envs, flash-attn, flash-attn-cute, etc. ``` The `envs` extra installs environments listed under `[project.optional-dependencies].envs`, resolved through `[tool.uv.sources]`. Adding a new env means adding its package name to `envs` and its editable source path to `[tool.uv.sources]`. When bumping a package past the workspace-wide `exclude-newer = "7 days"` window, add it (and any newly-required transitives) to `[tool.uv.exclude-newer-package]` before refreshing `uv.lock`. ## Optional extras ### NemotronH (Mamba SSD kernels) ```bash CUDA_HOME=/usr/local/cuda uv pip install mamba-ssm ``` Requires `nvcc`. Without `mamba-ssm`, NemotronH falls back to HF's pure-PyTorch SSD path, which computes softplus in bf16 and yields ~0.4 KL divergence vs vLLM. Do **not** install `causal-conv1d` unless your GPU arch matches the prebuilt kernels — the code falls back to `nn.Conv1d` when it's absent. ### FP8 inference (GLM-5-FP8, etc.) ```bash uv sync --group fp8-inference # installs the prebuilt deep-gemm wheel ``` ### Trainer DeepEP backend `scripts/install_ep_kernels.sh` auto-detects the CUDA toolkit matching torch and the GPU arch, builds NVSHMEM + DeepEP from source, and skips if `deep_ep` already imports. ```bash bash scripts/install_ep_kernels.sh ``` Flags: `--workspace DIR`, `--deepep-ref REF` (default `73b6ea4`), `--nvshmem-ver VER` (default `3.3.24`), `--configure-drivers` (multi-node IBGDA; needs sudo + reboot). Verify: `uv run python -c 'import deep_ep; print(deep_ep.__file__)'`. ## Key files - `pyproject.toml` — dependencies, extras, dependency groups - `uv.lock` — pinned lockfile (refresh with `uv sync --all-extras`) - `scripts/install.sh` — bootstrap installer - `scripts/install_ep_kernels.sh` — DeepEP build script
From useplato/prime-rl, Apache-2.0.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 18, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/useplato/prime-rl
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
Cite this page
install skill. Agent Mart. https://agentmart.dev/skills/useplato-install (last updated 2026-10-24)