# vLLM adds day-0 support for Kimi K3.1 Pro on NVIDIA, AMD, TPU and T-Head

> Original title: vLLM Delivers Day-0 Support for Kimi K3.1 Pro

- Source: vLLM Blog
- Published: 2026-11-04T00:00:00.000Z
- Bad Influence: https://badinfluence.news/items/nz3mzl1o7dj7zkl60xk9la6oh
- Original: https://vllm.ai/blog/2026-11-04-kimi-k31-pro

## Summary

vLLM says it supports Moonshot AI's Kimi K3.1 Pro on day 0 across NVIDIA GPUs, AMD GPUs, Google TPUs and Alibaba T-Head PPUs. The post says the model adds Sparse Attention (DSA) to all 24 full-attention layers, and that vLLM packs its MLA latent, indexer keys and KDA state into one KV cache. vLLM also reports up to 1.69× faster time to first token than head-sharded prefill at 340K tokens on 8× GB300.

## Why it matters

The post explains the sparse attention design and KV cache layout behind day-0 serving, useful for engineers planning long-context deployments of large open-weight models.