---
name: "vllm-ascend-benchmark"
description: "Measure throughput and latency of a vLLM online service with a specified workload, including request-rate and concurrency sweeps. Use for 跑 benchmark, 压测, or 测吞吐. Code baseline-versus-candidate comparisons and performance regression decisions use vllm-ascend-performance-regression; accuracy and service lifecycle have separate workflows."
---

<!-- Generated from .agents/skills/vllm-ascend-benchmark/SKILL.md. Do not edit. -->

# vllm-ascend-benchmark

Read `.agents/skills/vllm-ascend-benchmark/SKILL.md` and only the references needed
for the current task. The canonical skill owns the workflow.