跳到正文
@TencentHunyuan· @TencentHunyuan · X·· 2026-09-01精选AI 评分72
AI 导读

腾讯混元称 Hy4 preview 在 AI 研究中自行发现推理瓶颈,通过算子融合与通信优化把端到端吞吐提升 31.8%,且在不同上下文长度和并发下保持稳定。该模型此前以 770B 总参数、49B 激活参数、1M 上下文发布,主打生产力与开源前沿,并给出博客、HuggingFace 和 GitHub 入口。

推荐理由

官方给出模型自主定位推理瓶颈并完成优化的具体数字,可供观察自我优化在推理侧的落地方式。

正文

One more thing about Hy4 preview that is particularly interesting.
In AI research. Hy4 preview found inference bottlenecks on its own and lifted e2e throughput 31.8% via operator fusion and comms opts — stable across context lengths and concurrency.
MORE ON: https://t.co/MXVjtIFxeh

引用@TencentHunyuan@TencentHunyuan
🚀 Hy4 preview is here. 770B, 49B active, 1M context. Built for productivity. Open source frontier. Consistent affordable price. Use it. Tell us what breaks. More on Hy blog:https://t.co/rbl1IWRk3C HuggingFace:https://t.co/mE9wevH5XR Github:https://t.co/pyl9zckpoL https://t.co/4iW6gSuZKr
在 X 查看被引用的帖子

来源:@TencentHunyuan · x.com