---
type: "raw_signal"
id: "announcing-new-vllm-and-sglang-inference-engines-on-6844b4"
slug: "announcing-new-vllm-and-sglang-inference-engines-on-6844b4"
title: "Announcing New vLLM and SGLang Inference Engines on TPU"
description: "Google announced native PyTorch backends for vLLM and SGLang on TPU, built on TorchTPU in collaboration with Inferact and RadixArk."
retrieval_nugget: "Google announced native PyTorch backends for vLLM and SGLang on TPU, built on TorchTPU in collaboration with Inferact and RadixArk."
observed_at: "2026-10-20"
record_date: "2026-10-20"
date_kind: "observed_at"
why_it_matters: "Google announced native PyTorch backends for vLLM and SGLang on TPU, built on TorchTPU in collaboration with Inferact and RadixArk. The engines retain each framework’s worker model, scheduler, KV-cache manager and API server while adding TPU implementations beneath them. Google lists prefix caching, host and Managed Lustre KV-cache offload, disaggregated prefill/decode, multimodal support and long"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "developers.googleblog.com"
topics: ["google"]
entities: ["Google","vLLM","SGLang","TorchTPU","Inferact","RadixArk","TPU Sync","Ironwood TPU"]
related_patterns: ["harness-architecture-outlives-model-choice"]
novelty_label: "new_fact"
what_changed: "Google now announces the launch of native PyTorch vLLM and SGLang inference engines on TPU, extending the earlier partnership teaser about TPU kernels and TorchTPU."
prior_refs: ["memory:20cf8138-48ea-88de-a3ec-5e09833b5963"]
source_url: "https://developers.googleblog.com/announcing-new-vllm-and-sglang-inference-engines-on-tpu"
source_urls: ["https://developers.googleblog.com/announcing-new-vllm-and-sglang-inference-engines-on-tpu"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:announcing-new-vllm-and-sglang-inference-engines-on-6844b4"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/announcing-new-vllm-and-sglang-inference-engines-on-6844b4/","markdown":"https://newruntime.com/signals/announcing-new-vllm-and-sglang-inference-engines-on-6844b4.md","json":"https://newruntime.com/signals/announcing-new-vllm-and-sglang-inference-engines-on-6844b4.json"}
---

# Announcing New vLLM and SGLang Inference Engines on TPU

## Retrieval answer

Google announced native PyTorch backends for vLLM and SGLang on TPU, built on TorchTPU in collaboration with Inferact and RadixArk.

Google announced native PyTorch backends for vLLM and SGLang on TPU, built on TorchTPU in collaboration with Inferact and RadixArk. The engines retain each framework’s worker model, scheduler, KV-cache manager and API server while adding TPU implementations beneath them. Google lists prefix caching, host and Managed Lustre KV-cache offload, disaggregated prefill/decode, multimodal support and long-context features. The company says the engines are running with preview customers and reports public benchmark results; these are company-reported claims, not independent validation. Source: https://developers.googleblog.com/announcing-new-vllm-and-sglang-inference-engines-on-tpu

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Google](https://newruntime.com/topics/google.md): Explore the google topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)