2411.01783v2
CC BY 4.0
上下文並行:可擴展的百萬 Token 推理
Context Parallelism for Scalable Million-Token Inference
Amy Yang, Jingyi Yang, Aya Ibrahim, Xinfeng Xie, Bangsheng Tang, Grigory Sizov, Jeremy Reizenstein, ...
LLMInferenceLong ContextParallelismRing Attention系統優化
kerg kerg 許願