Allen School researchers receive Best Paper Award for speeding up LLM performance with FlashInfer - Allen School News A team of University of Washington and NVIDIA researchers developed a system that can help make large language models (LLMs) faster and more adaptable. The researchers introduced FlashInfer, a versati...

#UWAllen & NVIDIA researchers earned a #MLSys2025 Best Paper Award for developing FlashInfer to boost #LLM performance—showing “what’s possible when academia, industry and the open-source community innovate together,” says @yzh119.bsky.social.‬ #AI #UWdiscovers news.cs.washington.edu/2025/07/01/a...

The PyTorch Foundation is a Gold Sponsor of #MLSys2025 this week in Santa Clara.

Visit the booth and explore talks from Soumith Chintala, Ion Stoica, and Exec Dir Matt White on open source AI and scalable ML systems.

🔗 pytorch.org/blog/pytorch...

#PyTorch #OpenSourceAI #AIInfrastructure

The #MLSys2025 program is up and registration is open! Check out accepted papers at mlsys.org/virtual/2025... and sign up to attend at mlsys.org/Register.