research
∙
08/19/2023
GNNPipe: Accelerating Distributed Full-Graph GNN Training with Pipelined Model Parallelism
Current distributed full-graph GNN training methods adopt a variant of d...
share
research
∙
05/16/2023
SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification
The high computational and memory requirements of generative large langu...
research
∙
07/20/2022
