Efficient Inference of Masked Diffusion Language Models on AMD XDNA2 NPU
Video by PyTorch via YouTube Ravi Gupta, Shiksha Patel, and Rishi Madduri (AMD) will present “Efficient Inference of Masked Diffusion Language Models on AMD XDNA2 NPU” at #PyTorchCon North America 2026. Their poster presents a power-efficient deployment of LLaDA-8B-Instruct on an AMD NPU. On a Ryzen AI MAX+ 395 APU at sequence length 128, the … Read more