Channel
Digests from NVIDIA Developer — NVIDIA Developer videos on accelerated computing, CUDA, GPUs, and AI systems.
This tutorial details deploying a standalone VLM kiosk on NVIDIA Jetson using Codex. The process involves local asset serving, configuring automatic full-screen startup, and verifying local inference without cloud dependency.
Read article
Evaluating open models requires moving beyond simple scores. The focus is now on agentic use cases, balancing intelligence, cost, and speed across multi-turn tasks. Learn about quantization and rigorous benchmarking.
Read article
Learn how to set up an NVIDIA Jetson for remote AI development. This guide covers secure SSH setup, Wi-Fi configuration, Codex CLI integration, and validating CUDA GPU access via Docker containers.
Read article
Smart routing for hybrid AI uses the PGX to route queries between local and cloud models, drastically cutting cloud token costs and regaining control of IT AI spend.
Read article
Learn how to build scalable visual AI agents from a single natural language prompt using NVIDIA Cosmos and VSS 3.3. Discover techniques like Adaptive Efficient Video Sampling (EVS) to optimize video processing costs and latency.
Read article
Factory Playback unifies siloed manufacturing data by using NVIDIA Cosmos and Metropolis VSS to turn raw video into a searchable, replayable record. Learn how to achieve root cause analysis on the shop floor.
Read article
Discover agentic development on NVIDIA Jetson. Learn how coding agents and specialized Jetson skills accelerate edge AI development, enabling complex VLM pipelines on resource-constrained devices.
Read article
Learn how NVIDIA NeMo Relay captures the full execution path of a Hermes Agent. This tutorial shows developers how to inspect the tools an AI agent used, the data it accessed, the tokens it consumed, and the cost of the run.
Read article
Learn how H-Company optimizes VLM serving for computer-use agents using NVIDIA Dynamo. Discover techniques like embedding caching, Model Express, and advanced routing to scale complex, multi-modal AI workloads.
Read article
NVIDIA OpenShell 0.1 provides a secure runtime boundary for AI agents, preventing compromised agents from executing unauthorized actions. It allows developers to deploy agents in a sandboxed environment where all components inherit consistent policy, credential, and audit controls.
Read article
Discover how local AI is redefining compute sovereignty. Learn about running Nemotron 3.5 Lightning on DGX Spark and DGX Station, and how unified stacks enable high-performance, private LLM inference.
Read article
Motif detailed their strategy for achieving a top 5 AA II score with limited resources. They emphasized that rigorous engineering, failure-driven SFT, and advanced techniques like Differential Attention are key to building world-class AI systems.
Read article
Discover how 'vertically integrated, horizontally open' AI factories are powered by CUDA. Learn how reusable libraries and Agentic AI are redefining the full-stack computing landscape.
Read article
Learn how to evaluate AI agent skills using SkillEvaluator. This multi-tier framework checks for security risks (prompt injection, data exfiltration) and measures 'Skill Lift' across five dimensions to ensure reliability in production workflows.
Read article
Two winning hack projects, LifeKit and Memo, demonstrate local AI on the GN100. They showcase advanced edge computing, using Neotron and Cosmos for offline survival guidance and wearable memory assistance.
Read article
Learn how NVFP4 compares to BF16 for Nemotron 3.5 Lightning. Discover how this low-precision format shrinks memory footprint and boosts inference speed without a major quality hit.
Read article
NVIDIA experts detail the Nemotron post-training pipeline, explaining how structured data, NeMo Gym, and MOPD are used to build agentic LLMs. Learn about data bias mitigation and the evolution from pre-training.
Read article
Discover how local AI is transforming critical fields. NVIDIA winners showcased Kerberos, a shared spatial-awareness system for SAR, and VELA, a voice-first, consent-controlled healthcare action system, both running locally on the GB10.
Read article
TensorRT Model Connect simplifies the path from open-source models to deployable applications. It provides a consistent workflow to convert models into optimized bundles, supporting everything from LLMs to video generation on multi-device setups.
Read article
Domyn outlines building sovereign AI models for regulated industries using advanced techniques like model compression, CPT, and RL. They detail custom tooling (Swarm, FinalFlows) essential for managing large-scale ML pipelines.
Read article