←新闻详情

通义千问 / Qwen更新于 10月14日 22:32

Qwen 祝贺 TokenSpeed 实现 685 tokens/s

Congrats to @lightseekorg on the impressive TokenSpeed results! 🚀 Great to see Qwen3.8-Flash-Next reaching 685 output tokens/s per user on Nvida GPUs. Excited t

AI 导读

祝贺 @lightseekorg 取得令人印象深刻的 TokenSpeed 成果！🚀 很高兴看到 Qwen3.8-Flash-Next 在 Nvida GPU 上达到每用户 685 output tokens/s。期待社区进一步释放 Qwen 的推理潜力！

打开来源网站

主题

标签

引用

LightSeek Foundation

@lightseekorg

685 output tokens/s per user on @Alibaba_Qwen Qwen3.8-Flash-Next. Running TokenSpeed on 4× NVIDIA GB300 with NVFP4. A look at the kernel and serving optimizations behind the results: 👉 https://t.co/ngSITTWNai ⭐ https://t.co/MJzhCEg7m8 https://t.co/CmIBYUTm5M

查看原帖

正文

当前显示原文，中文全文译文尚未就绪。

Congrats to @lightseekorg on the impressive TokenSpeed results! 🚀 Great to see Qwen3.8-Flash-Next reaching 685 output tokens/s per user on Nvida GPUs. Excited to see the community unlock more of Qwen’s inference potential!

来源

通义千问 / Qwen