# vLLM and Inferact push vLLM performance on Google TPUs with Kimi K3 megakernel

> Original title: Thanks to @SemiAnalysis_ for highlighting the vLLM ecosystem’s work on TPU, in particular the Kimi K3 megakernel and vLLM TorchTPU poweri...

- Source: vLLM
- Published: 2026-11-05T19:30:03.000Z
- Bad Influence: https://badinfluence.news/items/sifs2iza47n0oc2yhg8fyfaz3
- Original: https://x.com/vllm_project/status/2118425632602558511

## Summary

vLLM project thanks SemiAnalysis for highlighting its TPU work, including the Kimi K3 megakernel and vLLM TorchTPU powering AgentX results across GLM-5.2, Qwen3.5 397B, and Kimi K3. The post credits Inferact and Google Cloud for pushing vLLM performance on TPU and points readers to SemiAnalysis's write-up on TPU inference.

## Post

Thanks to @SemiAnalysis_ for highlighting the vLLM ecosystem’s work on TPU, in particular the Kimi K3 megakernel and vLLM TorchTPU powering AgentX results across GLM-5.2, Qwen3.5 397B, and Kimi K3. 

Shoutout to @inferact and @googlecloud for pushing vLLM performance on TPU. The @SemiAnalysis_ write-up below is a great read 👇

## Quoted post @SemiAnalysis_

> The Iron(wood) Throne: 
> Google's TPU Stakes Its Claim on Inference
> Viable Alternative of CUDA Moat, 
> NVIDIA Working Nights & Weekends, 
> Jensen’s Counter Submission, Kimi K3, 
> Meta Muse Spark Open, GLM5.3, 
> TorchTPU, SGLang, vLLM, llm-d, Ray 
> https://newsletter.semianalysis.com/p/tpu-strikes-the-king

https://x.com/SemiAnalysis_/status/2118419869091713083