发生了什么: vLLM Reaches 25K Total TPS/GPU on Qwen3.5

vLLM achieved 25,000 tokens per second per GPU serving Qwen3.5 on GB200 NVL72 systems using disaggregated prefill-decode architecture.

为何重要: vLLM Reaches 25K Total TPS/GPU on Qwen3.5

Matters for engineers deploying large language models at scale who need to maximize inference throughput on multi-GPU clusters with hybrid attention architectures.

注意: vLLM Reaches 25K Total TPS/GPU on Qwen3.5

Results use fixed 8K input and 1K output sequence lengths on random data; real-world performance varies with actual workload patterns and sequence length distributions.

新闻

vLLM Reaches 25K Total TPS/GPU on Qwen3.5

vLLM · vLLM Team · 发布于 2026年8月6日 · 阅读约3分钟

30秒读懂

发生了什么: vLLM achieved 25,000 tokens per second per GPU serving Qwen3.5 on GB200 NVL72 systems using disaggregated prefill-decode architecture.
为何重要: Matters for engineers deploying large language models at scale who need to maximize inference throughput on multi-GPU clusters with hybrid attention architectures.
注意: Results use fixed 8K input and 1K output sequence lengths on random data; real-world performance varies with actual workload patterns and sequence length distributions.

收听本摘要

阅读完整文章

llm
kernel
serving
vllm
qwen

这条新闻背后的模式

每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。

The Agent Architect

每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。

每周一封邮件,一键退订。您的地址仅用于发送简报。