Profile Vllm Performance

Profile vLLM and RT-VLM inference to identify and remove GPU-idle gaps, underfilled batches, transfer stalls, serialized multimodal work, scheduler gaps, or KV pressure. Use this skill when GPU utilization is unexpectedly low or bursty, capacity trails another runtime, TTFT or ITL regresses, or multimodal prefill and decode appear serialized. Not for running a first benchmark without a reproducible fixed-load signal.

NVIDIA-AI-Blueprints Updated

File contents

nvidia-ai-blueprints/video-search-and-summarization commit 34916a1120

Frequently asked questions

npx get-skill add nvidia-ai-blueprints/profile-vllm-performance