SGLang, vLLM, TensorRT LLM, TileRT, TokenSpeed 및 AMD의 ATOM을 사용하여 SLURM 클러스터에 분산 된 LLM inference 벤치 마크를위한 명령 라인 도구. 복잡한 쉘 스크립트와 50+ CLI 플래그를 선언 schema: 2] YAML 레시피로 대체하십시오: engine: 엔진 이름, roles:] 각 작업자 역할을 설명하고, services:]은 근로자 옆에 모든 것을 다룹니다.

문서: https://nvidia.github.io/srt-slurm/ (docs/; Agent: llms.txt)

빠른 시작

설치는 클러스터 별 설정 커버; 예제 / 실행 가능한 조리법, frontend 및 topology 당 하나.

에이전트가 그것을 구동하자

srtctl은 Claude Code, Codex 또는 Cursor를 가르치는 기술을 배로 체크 아웃을 설정하는 방법, srtslurm.yaml, 저자 및 검증 된 요리법을 작성하고 결과를 읽습니다. 체크 아웃에 설치하고 에이전트가 체크 아웃을 손으로 :

srtctl-mcp 서버, 편집기용 JSON Schema, llms.txt]는 문서에 설명되어 있습니다.

문서가있는 곳

• 조리법을 작성 : 조리법 가이드, 그 주제는 링크 (엔진, topology, frontends, 벤치 마크, 서비스, …)

srtctl

Command-line tool for distributed LLM inference benchmarks on SLURM clusters using SGLang, vLLM, TensorRT LLM, TileRT, TokenSpeed and AMD’s ATOM. Replace complex shell scripts and 50+ CLI flags with a declarative schema: 2 YAML recipe: engine: names the engine, roles: describes each worker role, and services: covers everything launched next to the workers.

Documentation: https://nvidia.github.io/srt-slurm/ (source in docs/; agents: llms.txt)

Quick Start

git clone https://github.com/NVIDIA/srt-slurm.git
cd srt-slurm
uv sync --no-dev

# One-time setup: downloads etcd, NATS, uv and the tachometer binaries for the
# compute nodes' architecture and writes srtslurm.yaml (account, partition, GPUs per node)
make setup ARCH=aarch64  # or ARCH=x86_64

uv run srtctl dry-run -f examples/sglang/dynamo-agg.yaml   # render without submitting
uv run srtctl apply   -f examples/sglang/dynamo-agg.yaml   # submit

Installation covers cluster-specific setup; examples/ has runnable recipes, one per frontend and topology.

Let an agent drive it

srtctl ships a skill that teaches Claude Code, Codex or Cursor how to set up a checkout, write srtslurm.yaml, author and validate recipes, submit them, and read the results. Install it into the checkout and hand the agent the checkout:

uv run srtctl skill --target claude    # .claude/skills/srtctl/SKILL.md
uv run srtctl skill --target codex     # .codex/skills/srtctl/SKILL.md
uv run srtctl skill --target cursor    # .cursor/rules/srtctl.mdc

The srtctl-mcp server, the recipe JSON Schema for editors, and llms.txt are described in the documentation home.

Where things are documented

• Write a recipe: Recipe Guide, then the topic pages it links (engines, topology, frontends, benchmarks, services, …)
• Every field, type, default and allowed value: Schema Reference (generated from the code)
• Every command and flag: CLI Guide and CLI Reference (generated)
• Run and debug: Monitoring, SLURM FAQ
• Analyze: Profiling, DSight
• Old recipes: Legacy (v1) layout; srtctl migrate rewrites them