Picture for Chun-Feng Wu

Chun-Feng Wu

S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput

Add code
Jun 09, 2023
Figure 1 for S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput
Figure 2 for S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput
Figure 3 for S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput
Figure 4 for S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput
Viaarxiv icon