腾讯发布了Hy4预览版，770B参数模型能自发现推理瓶颈并提升31.8%吞吐量，1M上下文还开源。
腾讯混元Hy4预览版模型参数达770B，活跃参数49B，支持1M上下文长度。该模型通过算子融合和通信优化，自行发现推理瓶颈，将端到端吞吐量提升31.8%。性能在不同上下文长度和并发场景下保持稳定。模型面向生产力场景，采用一致且亲民的定价策略。
One more thing about Hy4 preview that is particularly interesting. In AI research. Hy4 preview found...
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: hy.tencent.ai Tencent Hy @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 hy.tencent.ai/research/hy4-p… C HuggingFace huggingface.co/tencent/Hy4-pr… R Github github.com/Tencent-Hunyua… L 🔗 View Quoted Tweet 💬 9 🔄 3 ❤️ 101 👀 4586 📊 19 ⚡