AI MODELS
Enhancing AI Model Efficiency with Quantization Aware Training and Distillation
Explore how Quantization Aware Training (QAT) and Quantization Aware Distillation (QAD) optimize AI models for low-precision environments, enhancing accuracy and inference performance.
GitHub Copilot Enhances Developer Experience with Multi-Model AI Integration
GitHub Copilot evolves by integrating multiple AI models to enhance developer workflows, offering flexibility and increased productivity, according to GitHub's recent announcement.
NVIDIA and NSF Partner to Propel U.S. Scientific Innovation with AI Models
NVIDIA collaborates with the National Science Foundation to enhance U.S. scientific research through the development of open AI models, aiming to boost America's global scientific leadership.
OpenAI's gpt-oss Models: A Competitive Edge in AI Open Source Development
OpenAI's recent release of the gpt-oss models marks a significant milestone in open-source AI development, offering competitive performance against proprietary models like o4-mini.
NVIDIA Boosts AI Performance with GB200 NVL72 and OpenAI gpt-oss Models
NVIDIA collaborates with OpenAI to enhance AI capabilities, achieving up to 1.5 million TPS with their GB200 NVL72 system, optimizing gpt-oss models.
OpenAI's GPT-OSS Models Now Optimized for NVIDIA RTX GPUs
OpenAI, in collaboration with NVIDIA, has optimized its open-source GPT-OSS models for NVIDIA RTX GPUs, enhancing local AI model performance and accessibility for developers.
Enhancing RAG Pipelines with NVIDIA's Advanced Nemotron Models
Explore how NVIDIA's Llama Nemotron models can improve retrieval-augmented generation (RAG) systems by enhancing query rewriting and reasoning capabilities.
Effective FP8 Training: Exploring Per-Tensor and Per-Block Scaling Strategies
Explore NVIDIA's FP8 training strategies, focusing on per-tensor and per-block scaling methods, for enhanced numerical stability and accuracy in low-precision AI model training.
NVIDIA's Llama 3.2 NeMo Retriever Enhances Multimodal RAG Pipelines
NVIDIA introduces the Llama 3.2 NeMo Retriever Multimodal Embedding Model, boosting efficiency and accuracy in retrieval-augmented generation pipelines by integrating visual and textual data processing.
NVIDIA Supports Google DeepMind's Gemma 3n on Jetson and RTX
NVIDIA announces support for Google DeepMind's Gemma 3n on Jetson and RTX platforms, enhancing AI capabilities across devices with optimized models.
GitHub Copilot Plans to Deprecate Key AI Models by Summer 2025
GitHub Copilot announces the deprecation of several AI models, including OpenAI GPT-4.5 and GPT-4o. Users are advised to transition to suggested alternatives by the specified dates.
NVIDIA's GR00T-Dreams Blueprint Revolutionizes Robot Learning with Synthetic Data
NVIDIA introduces the GR00T-Dreams blueprint, leveraging synthetic trajectory data to advance humanoid robot learning, enabling adaptation to new environments with minimal human input.
NVIDIA Unveils Advanced AI Models to Boost Autonomous Vehicle Development
NVIDIA introduces Cosmos Predict-2 and new developer tools, enhancing synthetic data generation and AV training for industry leaders like Oxa, Plus, and Uber.
NVIDIA Unveils Nemotron-H Reasoning Models for Enhanced Throughput
NVIDIA introduces the Nemotron-H Reasoning model family, delivering significant throughput gains and versatile applications in reasoning-intensive tasks, according to NVIDIA's blog.
FLUX.1 Kontext: Revolutionizing Image Editing with Multi-Modal Models
Black Forest Labs introduces FLUX.1 Kontext models, offering innovative image editing through text and image prompts, available now on Together AI.
