Jan 21, 2025 · The Stargate Project is a new company which intends to invest $500 billion over the next four years building new AI infrastructure for OpenAI in the United States. We will begin deploying $100 billion immediately.

The NVIDIA Blackwell architecture introduces substantial improvements in both raw computing power and architectural innovations. NVIDIA’s collaboration with OpenAI has focused on leveraging these capabilities transparently through Triton’s compiler infrastructure, particularly in two key areas: Matrix multiplications including flash attention

Apr 25, 2024 · OpenAI has become the first firm to receive Nvidia’s advanced AI processor DGX H200, hand-delivered by the firm’s CEO, Jensen Huang. The H200, billed as the world’s most powerful GPU, will...

Jan 28, 2025 · OpenAI Triton on NVIDIA Blackwell Boosts AI Performance and Programmability Matrix multiplication and attention mechanisms are the computational backbone of modern AI workloads. While libraries like NVIDIA cuDNN provide highly optimized...

5 days ago · OpenAI currently uses a variety of NVIDIA GPUs, including NVIDIA V100s, H100s, and A100s, but the Blackwell B200 is the most advanced GPU chip that brings significant performance uplifts over its ...

Oct 17, 2024 · Nvidia quietly launched a groundbreaking AI model that surpasses OpenAI’s GPT-4 and Anthropic’s Claude 3.5, signaling a major shift in the competitive landscape of artificial intelligence.

Apr 24, 2024 · In a move that underscores the close ties between two giants in the artificial intelligence industry, Nvidia CEO Jensen Huang personally delivered the first Nvidia DGX H200 to OpenAI’s office...

Apr 25, 2024 · Nvidia CEO Jensen Huang hand-delivered the world's first DGX H200 computer to OpenAI's CEO and president, continuing a trend of connecting OpenAI with bleeding edge AI compute power.

Jan 24, 2025 · NVIDIA has optimized the Llama 3.2 collection of models for great performance, demonstrating how full-stack software can adaptively unlock efficiency across diverse AI deployment environments. ... This new paradigm, first introduced with the OpenAI o1 model, enables models to “reason” by generating many intermediate tokens before outputting ...

Aug 1, 2024 · GenAI-Perf serves as the default benchmarking tool for assessing performance across all NVIDIA generative AI offerings, including NVIDIA NIM, NVIDIA Triton Inference Server, and NVIDIA TensorRT-LLM. It facilitates easy comparisons among different serving solutions that support the OpenAI-compatible API.