vLLM (@vllm_project) sessions at #PyTorchCon# NA 2026 show how teams are optimizing inference, working on PyTorch release validation and compatibility, and using vLLM in broader serving and application workflows. Speakers will cover CUTLASS, Triton, and Helion; faster model loading with fastsafetensors; quantization and HiFloat; autonomous kernel bring-up and Intel GPU optimization; PyTorch release validation, enterprise agentic inference, stable ABI, and dynamic shapes; vision-language serving; cloud-to-edge workflows; high-speed storage; a serving stack for a physics-constrained generative model; and contributor onboarding and first-PR workflows. Featured speakers include: @nvidia: Michael Goldfarb, Guray Ozen, Aastha Jhunjhunwala, and @MarkMoyou @Meta: Andrey Talman, @janeyx99, and Laith Sakka @Arm: Kavya Sri Chennoju @IBM: Takeshi Yoshimura and Nili Guy @RedHat: Markell Rawls, Joseph Groenenboom, Tyler Michael Smith, Sean McGovern, Christopher Leonard, and Maroon Ayoub @Google: Ankita Luthra and Trinadh Kotturu @intel: Xiaogang Gu, Qun Yang, Whitney Tsang, and Artur Fierka @Huawei: Yun Zhao and Haonan Zhang @IBMResearch: Burkhard Ringlein @UMNews: @arunshar08 Register by September 4 to save: Read the vLLM session guide: