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. At the… The post Optimizing Muse Spark Open on TPU v7 with SGLang-TorchTPU appeared first on PyTorch .
Optimizing Muse Spark Open on TPU v7 with SGLang-TorchTPU
calendar_today
November 10, 2026
person
Haolin Fu, Xiaoyu Zhang, Junyan Xu, Wangyuan Zhang, Haoguang Cai, RadixArk Team
domain
pytorch