sglang-auto-benchmark

Community

Automate AI benchmark workflows end-to-end.

AuthorNabilhassan12345
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Automates and orchestrates AI benchmark workflows by coordinating SGLang auto-benchmark runs across tiered server-flag sweeps, canonical dataset preparation, and result export.

Core Features & Use Cases

  • Supports tiered search configurations, resumeable runs, and remote/local deployments for reproducible benchmarking.
  • Manages dataset preparation, model launch commands, and result aggregation to compare configurations efficiently.
  • Use Case: A team wants to compare QPS and latency tradeoffs across multiple model backends on their own infra.

Quick Start

Start a benchmark run from a prepared config and let the agent orchestrate flag sweeps, dataset canonicalization, and summary generation.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: sglang-auto-benchmark
Download link: https://github.com/Nabilhassan12345/voice-ai-workspace/archive/main.zip#sglang-auto-benchmark

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.