NVIDIA Explains How AI Agents Work: Inside Agentic Inference
NVIDIA Developer · youtube · 2026-10-15
An NVIDIA Developer video breaks down how AI agents actually run: how tool calls, subagents, and growing context change inference workloads versus a single prompt; why fixed-length tests and recorded-session replay measure different things; and how to interpret interactivity, latency, concurrency, and throughput. It also maps where NVLink, NVIDIA Dynamo, NVFP4, and TensorRT-LLM fit, backed by blog posts on Vera Rubin/Blackwell agentic performance-per-watt benchmarks and Dynamo's distributed inference architecture.
More from coding & agent
- Isolating Antigravity chats per subfolder with AGY Rules and PreInvocation Hooks — bibryam · 2026-10-16
- Gemini shown off modding Minecraft to turn players into any Spider-Man — zacharynado · 2026-10-16
- Workflow: annotate UI screenshots in tldraw, hand to Claude, get better UI — max__drake · 2026-10-16
- Beyond chat wrappers: designing stateful, multimodal AI apps as interaction conductors — dr_cintas · 2026-10-16
- IBM engineer maps 5 levels of AI coding, from manual to a 3-day agent software factory — TejasKumar_ · 2026-10-16
- 10 open-source repos that let your AI agent reverse-engineer apps and games — victor_explore · 2026-10-16