# Open-source SGLang plugin adds inference serving support for IBM Spyre

_Published Thursday, November 12, 2026 at 9:49 AM EST · AI, Infrastructure · Latest · Tier 2 — Notable_

![Open-source SGLang plugin adds inference serving support for IBM Spyre — Primary](https://pytorch.org/wp-content/uploads/2026/11/All-PyTorch-Blog-Social-Images-6.png)

Developers working on IBM's Spyre AI accelerator have made an open-source plugin available that connects the hardware to SGLang, software for serving AI models. In a PyTorch blog post, the team reported approximately 3.6× the throughput of its reference PyTorch inference implementation using torch-spyre.

The two-person team built the integration in less than a week with AI coding agents, reusing existing PyTorch hardware support. SGLang's prefix sharing, which reuses processing for shared prompt beginnings, worked without Spyre-specific changes. Performance matched vLLM across the measured workloads for Granite 3.3 8B and Gemma 4 26B A4B; installation requires the plugin and compatibility patches.

## Sources

- [PyTorch](https://pytorch.org/blog/integrating-sglang-into-spyre-in-under-a-week-with-ai/)

---
Canonical: https://techandbusiness.org/newswire/7agv-z6aOXAiT3fg9onT2x
Published: 2026-11-12T14:49:45.476Z
Story chronology: 2026-11-12T14:45:25.000Z
Retrieved: 2026-11-12T16:47:47.399Z
Publisher: Tech & Business (techandbusiness.org)