Startup Buzz / New product
SGLang-TorchTPU
by SGLang
AISGLang has launched SGLang-TorchTPU, a TPU plugin for SGLang built with Google's TPU team and Meta's PyTorch team. The plugin lists Muse Spark Open, GLM-5.3 Flash, Kimi K3, Ling 3.1 Flash, and MiniMax H3 among supported open models. It also includes a custom MegaKernel, with Muse Spark Open reaching 770 tok/s decode at bs=1 on InferenceX 8K/1K, and is available on GitHub.
Why it matters: The post gives the plugin's supported models and a specific decode speed on InferenceX, letting readers judge what the TPU support covers.
Original source
Open original ↗Recorded launch evidence
Today we launch SGLang-TorchTPU, built with @Google TPU team and Meta @PyTorch team. ... SGLang-TorchTPU is available now: http://github.com/sgl-project/sglang-torchtpu
Loading source…
Descriptions are prepared from the linked sources. Inclusion is not an endorsement.