SGLang Partners with Google Cloud and RadixArk to Make TPU a Cost-Efficient Path for Frontier Inference
ying11231 · x · 2026-08-01
RadixArk, Google Cloud, and the SGLang community are collaborating to make TPU a drop-in, cost-efficient path for frontier LLM inference.
SGL-JAX already supports running major open-source models (like Gemma, Qwen, DeepSeek, etc.) on the latest TPU generations. This partnership brings SGLang's production-ready features—such as 5D parallelism, Radix Cache, and speculative decoding—to TPU. Furthermore, SGL-torchtpu will be introduced later this year as a PyTorch-native backend, enabling developers to run LLMs on TPUs using standard PyTorch tooling.
Related event: SGLang Joins Google Cloud and RadixArk to Bring TPU Inference(6 posts)→
More from Infra
- Meta's commitments jumped to $349B in a quarter as server memory prices tripled ahead of Oct 21 earnings — tengyanAI · 2026-10-16
- Meta releases Muse Spark Open, trained with vLLM-powered RL inference from day one — colinmcnamara · 2026-10-16
- Meta's open Muse Spark needs 493GB of memory — far beyond any consumer laptop — TejasKumar_ · 2026-10-16
- CoreWeave plunges 20% as credit markets price >60% default odds; is this dot-com all over again? — kimmonismus · 2026-10-16
- MiniCPM-V 4.7 35B-A3B hits 17+ tokens/s on iPad with ~3GB memory — techNmak · 2026-10-16
- China rolls out 'token factories' and a 2026-28 token economy action plan — nordicinst · 2026-10-16