Picture for Yichu Zhang

Yichu Zhang

Hermes: Memory-Efficient Pipeline Inference for Large Models on Edge Devices

Add code
Sep 09, 2024
Figure 1 for Hermes: Memory-Efficient Pipeline Inference for Large Models on Edge Devices
Figure 2 for Hermes: Memory-Efficient Pipeline Inference for Large Models on Edge Devices
Figure 3 for Hermes: Memory-Efficient Pipeline Inference for Large Models on Edge Devices
Figure 4 for Hermes: Memory-Efficient Pipeline Inference for Large Models on Edge Devices
Viaarxiv icon