NVIDIA AI Blueprint for Video Search and Summarization (VSS) is a reference architecture for applications that use AI to search, analyze, question, and summarize live or recorded video. It is intended for building video analytics agents with vision-language models, language models, retrieval-augmented generation, and NVIDIA NIM microservices. The catalogue entries provide coding-agent rules, skills, commands, agents, instructions, and settings associated with the project.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NVIDIA-AI-Blueprints/video-search-and-summarization --skill profile-vllm-performancegit clone --depth 1 https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarizationWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/profile-vllm-performance)<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/profile-vllm-performance"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/profile-vllm-performance/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/profile-vllm-performance"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/profile-vllm-performance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.01275 |
| Opus 5.5 | $0.00037 | $0.00510 |
| Sonnet 5.5 | $0.00019 | $0.00255 |
| Haiku 4.5 | $0.00009 | $0.00128 |
Grade A, and why
profile-vllm-performance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 15d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Profile vLLM Performance
Find the dominant loss mechanism, prove it with a correlated timeline, make the smallest causal change, and validate the result with a matched A/B run. A capacity number or average GPU-utilization sample is not bubble attribution.
Freeze The Comparison
Record the exact code, container, model revision, precision, hardware, scheduler settings, workload shape, media, prompt, token budget, sampling, cache state, concurrency, and success criteria. Prove semantic correctness before optimizing. Do not compare runtimes when any of these dimensions differ unless that dimension is the declared variable.
Establish The Signal
- Verify actual output-token counts, successful work, fresh-stream coverage, dropped chunks, cancellations, and cleanup. Early EOS or silent failure is not throughput.
- Reproduce at fixed load below the knee, near the highest stable point, and just beyond it when practical. Keep capacity search separate from profiling.
- Record TTFT, inter-token latency, throughput, queue delay, batch size, scheduled tokens, active sequences, preemptions, KV occupancy, GPU memory, and phase durations available in the checked-out version.
- Use scenario-scoped DCGM or
nvidia-smi dmonfor the resource envelope and a short Nsight Systems or repository profiler capture for attribution. Profilers perturb timing; never use a profiled run as the capacity result.
Define a performance bubble as GPU-idle or low-occupancy time while eligible work is queued. Idle time caused by insufficient offered load is not a runtime bubble. If the scheduler queue is empty throughout every observed idle interval, first check whether eligible work is waiting upstream in media arrival, decode, preprocessing, or engine submission. Upstream waiting work is frontend or media starvation, not an offered-load gap. When neither the scheduler nor upstream stages have eligible work waiting, classify the result as insufficient offered load and make the first experiment a higher-fixed-concurrency replay with every other workload dimension unchanged. Do not recommend scheduler, kernel, batching, cache, prefill, or decode optimization until that replay shows GPU idle while eligible work remains queued.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 15d ago First seen · 113 lines · 93 tokens per session scan A f0aae01465e8
profile-vllm-performance is a skill published in the GitHub repository NVIDIA-AI-Blueprints/video-search-and-summarization (1,932 stars, last pushed today), licensed Apache-2.0. It adds 93 tokens to every session and 1,275 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other skills, from other repositories
rag-architecture-review
Review an existing Retrieval-Augmented Generation system and find why it underperforms. Use when asked to review or audit a RAG pipeline, diagnose wrong/ungrounded answers from a 'chat with your docs' feature, or improve an already-built knowledge assistant. Produces a staged review — ingestion, chunking, retrieval…
mistake-analyzer
Analyze incorrect answers from text, documents, or images; identify root causes of mistakes; classify error types; explain correct reasoning; and generate targeted improvement suggestions, wrong-question notebook entries, or similar practice questions. Use when the user provides a wrong answer, asks why they were…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
notebooklm
Install, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed async Python API. Use for notebook and source management, grounded chat and research, and artifact generation or download when the user mentions Gemini Notebook, notebooklm-py, the notebooklm CLI, or its Python API.…
google-cloud-solution-rag-enterprise-search-gke-sqldb
Discovers requirements, and generates architectural, design, and deployment guidance for a retrieval-augmented generation (RAG)-capable enterprise search system in Google Cloud. Use when users need a vector-enabled SQL database as the store and index for the embedding vectors, an open model and open-source inferencing…