DeepSeek AI is using 50,000 Nvidia H100 but workers "can't talk about it" because of U.S. export restrictions, according to CEO of Scale AI Alexandr Wang. The launch of the Chinese tech startup ...

It achieves performance comparable to Nvidia's H100 chip by combining two 910B processors into a single package through advanced integration techniques, they said. That means it has double the ...

The AI chip giant says the open-source software library, TensorRT-LLM, will double the H100’s performance for running inference on leading large language models when it comes out next month.

Nvidia said new benchmark test results show that the forthcoming H100 GPU, aka Hopper, raises the bar in per-accelerator performance when it comes to AI performance Six months after Nvidia ...