📌 📄 内容摘要:
龙傲天! (@dragonfsky) 在 Day 6 of #OpenSourceWeek: One More Thing – DeepSeek-V3/R1 Inference System Overview 中发帖
deepseek刚刚发布了
Optimized throughput and latency via:
🔧 Cross-node EP-powered batch scaling
🔄 Computation-communication overlap
⚖ Load balancing
Statistics of DeepSeek’s Online Service:
⚡ 73.7k/14.8k input/output tokens per second per H800 node
🚀 Cost profit margin 545%
💡 We hope this week’s insights offer value to the community and contribute to our shared AGI goals.
────────── 链接信息 ──────────
🔗 论坛链接: linux.do
📎 访问地址: https://linux.do/t/topic/464185/1
─────────────────────────────
📢 来源:LINUX DO | 标签:#OpenSourceWeek