PyTorch BlogTools
Optimizing Muse Spark Open on TPU v7 with SGLang-TorchTPU

TL;DR We serve Meta’s Muse Spark Open, an 816B-parameter mixture-of-experts model, on a single TPU v7 host of four chips, with SGLang running on the TorchTPU PyTorch backend.
Read at PyTorch Blog ↗Related

SiliconNVIDIA Expands Open Source Commitment With OpenShell Contribution and New AI Infrastructure NVIDIA Blog

SiliconRunning AV Reasoning Models Within Onboard Compute and Latency Limits NVIDIA Technical Blog

SiliconStart and Restore GPU Workloads in Seconds with NVIDIA Snapshot NVIDIA Technical Blog

SiliconManage Kubernetes Clusters for GPU Infrastructure with NVIDIA Kubernetes Engine NVIDIA Technical Blog

AsiaHow Nvidia CEO’s troubles, US midterms may tighten China chip curbs: ‘adding fuel to fire’ SCMP Tech
