Post
PyTorch
pytorch.org
did:plc:o3pmmtxoor73pszydv7pffsv
Running large Mixture-of-Experts models across pods creates two major challenges: expert traffic and KV-cache transfer.
At #PyTorchCon, Ravi Gupta, Rishi Madduri, and Shiksha Patel (AMD) will present how MoRI + vLLM tackles both.
https://hubs.la/Q04v4SL60
2026-10-10T16:00:35.256Z