Metropolis for Developers
…Then, curate, augment, and evaluate it with Cosmos for vision AI models. Get Started With Metropolis Start using the latest Metropolis vision language models and vision foundation models. NVIDIA Cosmos Reason Industry…
While model and agent evaluation are inextricably linked, their technical benchmarks and metrics for success are fundamentally different.
Mastering Agentic Techniques: AI Agent Evaluation | NVIDIA Technical BlogThe NVIDIA Model Optimizer (ModelOpt) library incorporates state-of-the-art model optimization techniques to compress and accelerate AI models. These techniques include quantization, distillation, pruning, speculative decoding, and sparsity. ModelOpt accepts Hugging Face, PyTorch, or ONNX format models as input and provides Python APIs for users to easily combine different optimization techniques to produce optimized checkpoints. ModelOpt supports highly performant quantization formats such as FP4, FP8, INT8, and INT4, and advanced algorithms including SmoothQuant, AWQ, SVDQuant, and Double Q
Model Quantization: Post-Training Quantization Using NVIDIA Model Optimizer | NVIDIA Technical BlogCLIP (Contrastive Language-Image Pretraining), introduced by OpenAI in 2021, is a foundation vision language model (VLM) that learns a shared embedding space for images and text through contrastive learning on large image-text pairs. Its ability to produce semantically aligned representations has made it a core building block across modern multimodal systems. The CLIP text encoder is widely reused as a conditioning module for text-to-image (Stable Diffusion, for example) and text-to-video (AnimateDiff, for example) synthesis. Its vision encoder serves as the visual backbone in multimodal LLMs
Model Quantization: Post-Training Quantization Using NVIDIA Model Optimizer | NVIDIA Technical Blog…Then, curate, augment, and evaluate it with Cosmos for vision AI models. Get Started With Metropolis Start using the latest Metropolis vision language models and vision foundation models. NVIDIA Cosmos Reason Industry…
…Model selection The four models selected span different sizes, memory footprints, and inference use cases (Table 1). This range enables evaluating fractional allocation across workloads with different memory footprints. Notably, the largest…
…Test-time scaling improved reasoning by giving models more generated tokens for thinking. Now, agentic AI and reinforcement learning scale actions. Models take more steps, call more tools, run more evaluations, and…
…AI Agent Evaluation Evaluating an AI model and evaluating an AI agent are related—but they answer fundamentally different questions. A model benchmark tests the capability of a... 6 MIN READ May…
…AI Agent Evaluation Evaluating an AI model and evaluating an AI agent are related—but they answer fundamentally different questions. A model benchmark tests the capability of a... 6 MIN READ May…
…As models grow in size and complexity, efficient data movement becomes increasingly important for optimal performance in areas such as: Model loading and initialization: Fast model loading is crucial for quick startup…
…Developers then assemble simulation scenes by assigning materials, enabling physics, and configuring robot and sensor models. From there, robots can be used with NVIDIA Isaac Lab for robot learning and simulated in…
…She combines her expertise in language modeling and AI evaluation with a commitment to developing trustworthy AI tools that prioritize transparency, safety and responsible deployment. View all posts by Pratyusha Maiti View…
Agentic AI / Generative AI Accelerating Long-Context Model Training in JAX and XLA Feb 03, 2026 By Sevin Fide Varoglu , Tejash Shah , Md Fahim Faysal Khan , TJ Xu and Arnav Goel Discuss…
…This lowers the cost for agentic tasks by up to 30%. Breakthroughs powering Nemotron 3 Ultra To mitigate the typical efficiency-accuracy tradeoffs for high-capacity reasoning models, the Nemotron models introduce…