Standalone · Tooling

srt-slurm: declarative LLM benchmarks on SLURM

Distributed LLM inference benchmarks are a mess of shell scripts and CLI flags. NVIDIA's srtctl replaces them with declarative YAML. Same benchmarks, less ceremony.

Benchmarking LLM inference on a SLURM cluster is a rite of passage that involves shell scripts, 50+ CLI flags, and a prayer. NVIDIA's srtctl replaces the whole mess with declarative YAML configuration, and it's the kind of tool you don't know you need until you've done it the hard way.

The problem

Distributed LLM inference benchmarks on SLURM clusters are painful. You need to launch TensorRT-LLM, SGLang, or vLLM across multiple nodes, coordinate the load, and collect the numbers. The traditional approach: complex shell scripts with dozens of flags, fragile across nodes, impossible to reproduce.

What srtctl does

srtctl is a command-line tool for distributed LLM inference benchmarks on SLURM clusters using TensorRT-LLM, SGLang, and vLLM. It replaces complex shell scripts and 50+ CLI flags with declarative YAML configuration.

Mental model

srtctl is to LLM benchmarks what Kubernetes is to deployments: you declare the desired state, and the tool makes it happen.

Why it matters

Benchmarking is how you decide what to deploy. If the benchmark harness is fragile, the decisions are suspect. Declarative config makes benchmarks reproducible, which makes the numbers trustworthy, which makes the deployment decision sound.

The takeaway

A benchmark you can't reproduce is a guess. Declarative config turns benchmarking into a repeatable experiment.

Sources

Back to the blog