원클릭으로 Manus에서 모든 스킬 실행

$pwd:

start-run

Name: Start Run
Author: PrimeIntellect-ai

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

Manus에서 실행

$ git log --oneline --stat

stars:1,413

forks:302

updated:2026년 5월 20일 21:27

SKILL.md

readonly

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

Start a run

All entrypoints run via uv run <command> and accept TOML configs via @ path/to.toml plus CLI overrides.

Config system at a glance

pydantic-config — Pydantic-based TOML + CLI loader. Highlights (see the configs skill for full mechanics):

Config files via @ path (TOML / YAML / JSON); CLI args layer on top, deep-merged with class defaults.
Nested groups via dotted CLI paths — kebab-case on the CLI, snake_case in TOML.
Bool toggles: bare --flag enables, --no-flag disables (nested too).
Lists: space-separated or JSON literal. Dicts: JSON literal, deep-merged with file values.
Optional sub-configs (WandbConfig | None): bare --wandb enables defaults; --wandb @ wandb.toml enables from a file; --no-wandb disables.
Discriminated unions are switched by the type tag (e.g. --optimizer.type muon).
Validation aliases let renamed fields keep working; legacy keys can be remapped in a model_validator(mode="before").
Auto-generated --help panels from Field(description=...) or PEP 224 docstrings.
Friendly errors: required-field boxes, validator errors point at the offending flag, unknown flags get a "did you mean" hint.

`rl` — RL training

Launches inference server, orchestrator, and trainer as subprocesses.

uv run rl @ examples/reverse_text/rl.toml
uv run rl @ examples/reverse_text/rl.toml @ examples/reverse_text/slurm_rl.toml   # SLURM
uv run rl @ examples/reverse_text/rl.toml --dry-run                                # write scripts, don't run

Config: RLConfig (packages/prime-rl-configs/src/prime_rl/configs/rl.py)
Entrypoint: src/prime_rl/entrypoints/rl.py
SLURM: single- and multi-node

`sft` — SFT training

Launches torchrun internally — never call torchrun directly.

uv run sft @ examples/reverse_text/sft.toml
uv run sft @ examples/reverse_text/sft.toml --slurm
uv run sft @ examples/reverse_text/sft.toml --dry-run

Config: SFTConfig (packages/prime-rl-configs/src/prime_rl/configs/sft.py)
Entrypoint: src/prime_rl/entrypoints/sft.py
SLURM: single- and multi-node

`inference` — vLLM server

OpenAI-compatible API plus prime-rl custom endpoints (/update_weights, /load_lora_adapter, /init_broadcaster). Always use this entrypoint — never vllm serve directly.

uv run inference @ configs/debug/infer.toml
uv run inference --model.name Qwen/Qwen3-0.6B --model.enforce-eager

Smoke checks:

curl http://<host>:<port>/health
curl http://<host>:<port>/v1/models
curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "Qwen/Qwen3-0.6B", "messages": [{"role": "user", "content": "Hi"}], "max_tokens": 50}'

Config: InferenceConfig (packages/prime-rl-configs/src/prime_rl/configs/inference.py)
Entrypoint: src/prime_rl/entrypoints/inference.py
SLURM: single-node, multi-node, and disaggregated deployments

Summary

Command	Purpose	Typical use
`rl`	Full RL pipeline	Production RL training
`sft`	Supervised fine-tuning	SFT and hard-distill
`inference`	vLLM server	Standalone serving / debugging

Key paths

src/prime_rl/entrypoints/ — rl, sft, inference (+ trainer, orchestrator for direct launches)
packages/prime-rl-configs/src/prime_rl/configs/ — all config classes
configs/debug/ — minimal debug configs
examples/ — full example configs (e.g. reverse_text/)

related-skills.json

같은 저장소

configs.md

from "PrimeIntellect-ai/prime-rl"

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.

2026-05-221.4k

release.md

from "PrimeIntellect-ai/prime-rl"

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

2026-05-201.4k

install.md

from "PrimeIntellect-ai/prime-rl"

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.

2026-05-201.4k

monitor-run.md

from "PrimeIntellect-ai/prime-rl"

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.

2026-05-201.4k

training.md

from "PrimeIntellect-ai/prime-rl"

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).

2026-05-201.4k

package.json

"author": "PrimeIntellect-ai"

"repository": "PrimeIntellect-ai/prime-rl"

GitHub 저장소 열기 Creator 저장소 보기

$ install --global

$ download --local

Manus에서 실행

$ useful --forSOC

데이터 과학자컴퓨터 및 수학직15-2051L4

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

Start a run

All entrypoints run via uv run <command> and accept TOML configs via @ path/to.toml plus CLI overrides.

Config system at a glance

pydantic-config — Pydantic-based TOML + CLI loader. Highlights (see the configs skill for full mechanics):

Config files via @ path (TOML / YAML / JSON); CLI args layer on top, deep-merged with class defaults.
Nested groups via dotted CLI paths — kebab-case on the CLI, snake_case in TOML.
Bool toggles: bare --flag enables, --no-flag disables (nested too).
Lists: space-separated or JSON literal. Dicts: JSON literal, deep-merged with file values.
Optional sub-configs (WandbConfig | None): bare --wandb enables defaults; --wandb @ wandb.toml enables from a file; --no-wandb disables.
Discriminated unions are switched by the type tag (e.g. --optimizer.type muon).
Validation aliases let renamed fields keep working; legacy keys can be remapped in a model_validator(mode="before").
Auto-generated --help panels from Field(description=...) or PEP 224 docstrings.
Friendly errors: required-field boxes, validator errors point at the offending flag, unknown flags get a "did you mean" hint.

`rl` — RL training

Launches inference server, orchestrator, and trainer as subprocesses.

uv run rl @ examples/reverse_text/rl.toml
uv run rl @ examples/reverse_text/rl.toml @ examples/reverse_text/slurm_rl.toml   # SLURM
uv run rl @ examples/reverse_text/rl.toml --dry-run                                # write scripts, don't run

Config: RLConfig (packages/prime-rl-configs/src/prime_rl/configs/rl.py)
Entrypoint: src/prime_rl/entrypoints/rl.py
SLURM: single- and multi-node

`sft` — SFT training

Launches torchrun internally — never call torchrun directly.

uv run sft @ examples/reverse_text/sft.toml
uv run sft @ examples/reverse_text/sft.toml --slurm
uv run sft @ examples/reverse_text/sft.toml --dry-run

Config: SFTConfig (packages/prime-rl-configs/src/prime_rl/configs/sft.py)
Entrypoint: src/prime_rl/entrypoints/sft.py
SLURM: single- and multi-node

`inference` — vLLM server

OpenAI-compatible API plus prime-rl custom endpoints (/update_weights, /load_lora_adapter, /init_broadcaster). Always use this entrypoint — never vllm serve directly.

uv run inference @ configs/debug/infer.toml
uv run inference --model.name Qwen/Qwen3-0.6B --model.enforce-eager

Smoke checks:

curl http://<host>:<port>/health
curl http://<host>:<port>/v1/models
curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "Qwen/Qwen3-0.6B", "messages": [{"role": "user", "content": "Hi"}], "max_tokens": 50}'

Config: InferenceConfig (packages/prime-rl-configs/src/prime_rl/configs/inference.py)
Entrypoint: src/prime_rl/entrypoints/inference.py
SLURM: single-node, multi-node, and disaggregated deployments

Summary

Command	Purpose	Typical use
`rl`	Full RL pipeline	Production RL training
`sft`	Supervised fine-tuning	SFT and hard-distill
`inference`	vLLM server	Standalone serving / debugging

Key paths

src/prime_rl/entrypoints/ — rl, sft, inference (+ trainer, orchestrator for direct launches)
packages/prime-rl-configs/src/prime_rl/configs/ — all config classes
configs/debug/ — minimal debug configs
examples/ — full example configs (e.g. reverse_text/)

start-run

Start a run

Config system at a glance

rl — RL training

sft — SFT training

inference — vLLM server

Summary

Key paths

이 저장소의 다른 Skills

이 저장소의 다른 Skills

Start a run

Config system at a glance

rl — RL training

sft — SFT training

inference — vLLM server

Summary

Key paths

`rl` — RL training

`sft` — SFT training

`inference` — vLLM server

`rl` — RL training

`sft` — SFT training

`inference` — vLLM server