**Serving LLMs on Tenstorrent Hardware: Inside the vLLM TT Plugin** > Tenstorre

**Serving LLMs on Tenstorrent Hardware: Inside the vLLM TT Plugin**

> Tenstorrent accelerators join vLLM as an out-of-tree platform plugin, driven by mesh-architecture choices: phase-based scheduling, single-process data paralleli Serving LLMs on Tenstorrent Hardware: Inside the vLLM TT Plugin September 7, 2026 16 min read Tenstorrent Team \# hardware \# ecosystem Supported models Why a Tenstorrent backend looks different Plugging in, not forking Phase-based scheduling: prefill-only or d...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：ai-products
- **发布时间**：2026-09-11 17:35（北京时间）
- **原文**：[打开原文](https://vllm.ai/blog/2026-09-07-vllm-tt-plugin)