Software Development
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.
- Publisher / source
- NVIDIA-AI-Blueprints/video-search-and-summarization (found on GitHub top repositories)
- Upstream record
- NVIDIA-AI-Blueprints/video-search-and-summarization
- Version
- Version 1
- Published
- Publication review
- Approved for publication
- Content fingerprint
f0aae01465e8fcbb36ffa4bbd1f42a89a966a85e079332cea459b6b38df83524