Sglang Auto Benchmark

Run SGLang auto benchmark searches with tiered server-flag sweeps, canonical dataset preparation, ShareGPT auto-download, custom-data conversion/validation, SLA or fixed-QPS benchmarking, CSV export, and optional second-stage speculative/EAGLE tuning. Use when the user wants an AI-operated benchmark workflow rather than a one-off bench_serving command.

openmoss Updated 808 repo stars
MOSS-VL Architecture

File contents

openmoss/moss-vl commit 21dd803208

Frequently asked questions

npx get-skill add openmoss/sglang-auto-benchmark