Kimi K3.1 Pro Gets Day-0 Inference Support on Google TPU
Google partnered with the vLLM and SGLang teams to provide day-0 distributed inference support for Moonshot AI's 2.8-trillion-parameter Kimi K3.1 Pro on TPU v7x, the model's first day-0 deployment on TPU hardware.
2026-11-06 ~ 2026-11-06 · 2 related posts
- Kimi K3.1 Pro gets Day-0 TPU support: serving a 2.8T-param MoE with llm-d on TPUs and GPUs — vllm_project · 2026-11-06
- Kimi K3.1 Pro gets day-0 vLLM support on Google's TPU v7x in joint collaboration — woosuk_k · 2026-11-06