DeepSeek @deepseek_ai
🚀 Day 6 of #OpenSourceWeek: One More Thing – DeepSeek-V3/R1 Inference System Overview
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
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
