Benchmark vLLM or OpenAI-compatible serving endpoints using vllm bench serve. Supports multiple datasets (random, sharegpt, sonnet, HF), backends (openai, openai-chat, vllm-pooling, embeddings), throughput/latency testing with request-rate control, and result saving. Use when benchmarking LLM serving performance, measuring TTFT/TPOT, or load testing inference APIs.
$npx -y skills add vllm-project/vllm-skills --skill vllm-bench-serveInstalls into the current project.
Run `npx skills use "https://github.com/vllm-project/vllm-skills" --skill "vllm-project/vllm-skills/vllm-bench-serve"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/vllm-project/vllm-skills" that are relevant to the current task. Run `npx skills add "https://github.com/vllm-project/vllm-skills"` and select the relevant skills, then follow their instructions.