No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL

Improving Hugging Face Training Efficiency Through Packing with Flash Attention 2

Building Cost-Efficient Enterprise RAG applications with Intel Gaudi 2 and Intel Xeon

Unlocking Longer Generation with Key-Value Cache Quantization

Unlocking asynchronicity in continuous batching

Behind “ANCESTRA”: combining Veo with live-action filmmaking

We partnered with Darren Aronofsky, Eliza McNitt and a team of more than 200 people to make a film using Veo and live-action filmmaking.

Optimum-NVIDIA Unlocking blazingly fast LLM inference in just 1 line of code