1
VoltanaLLM: Energy-Efficient LLM Serving
LLM服务节能新方案：利用预填充/解码解耦架构，动态GPU频率控制实现36.3%能耗节省
Article URL: https://supercomputing-system-ai-lab.github.io/projects/voltana/ Comments URL: https://news.ycombinator.com/item?id=48655520 Points: 2 # …
LLM服务节能新方案：利用预填充/解码解耦架构，动态GPU频率控制实现36.3%能耗节省
Article URL: https://supercomputing-system-ai-lab.github.io/projects/voltana/ Comments URL: https://news.ycombinator.com/item?id=48655520 Points: 2 # …