PrimeIntellect-ai/prime-rl

dashboard

Find, start, use, and stop the local run dashboard for metrics, configs, traces, logs, and reports. Use when asked for its URL, to watch or inspect a run, to control the open dashboard, or to create a cited dashboard report explicitly requested by the user.

Langue du texte source : anglais

monitor-run

Monitor an ongoing prime-rl training run — find the output directory, tail logs, check key metrics, inspect SLURM jobs, and restart safely. Use when asked to check on a run, debug training, or investigate performance.

Langue du texte source : anglais

training

Launch and monitor prime-rl training runs. Use when starting, supervising, or debugging an RL/SFT run. Routes to `start-run` (entrypoints + how to launch) and `monitor-run` (logs, metrics, check-ins).

Langue du texte source : anglais

configs

How the prime-rl config system works — TOML files, CLI overrides, composition, and special patterns. Use when creating configs, debugging config errors, or overriding values via CLI.

Langue du texte source : anglais

start-run

How to launch prime-rl training runs — the `rl`, `sft`, `inference`, and `evals` entrypoints, their config classes, and single-node/SLURM/dry-run modes. Use when starting a run or picking the right entrypoint.

Langue du texte source : anglais

install

How to install prime-rl and its optional dependencies. Use when setting up the project, installing extras like DeepEP for multi-node expert parallelism, or troubleshooting dependency issues.

Langue du texte source : anglais

kernels

How prime-rl vendors, builds, and ships CUDA kernels (the `deps/prime-kernels` submodule and the `prime-kernels` wheel). Use when adding a kernel, building it locally, calling one from training code, or publishing prebuilt wheels.

Langue du texte source : anglais

release

How to prepare and publish GitHub releases for prime-rl. Use when drafting release notes, tagging versions, or publishing releases.

Langue du texte source : anglais