Sglang Xpu Bench

Benchmark a **running SGLang-XPU server** on an Intel GPU using `sglang.bench_serving`. Measures TTFT, TPOT, ITL, end-to-end latency, and throughput against the OpenAI-compatible endpoint. Use after sglang-xpu-run. Not for vLLM servers (use vllm-xpu-bench) or no-server PyTorch (use torch-xpu-bench).

intel Updated 122 repo stars

File contents

intel/gpu-ai-skills commit 077eaac8b7

Frequently asked questions

npx get-skill add intel/sglang-xpu-bench