Picture for Archit Patke

Archit Patke

Characterizing GPU Resilience and Impact on AI/HPC Systems

Add code
Mar 14, 2025
Viaarxiv icon

Hierarchical Autoscaling for Large Language Model Serving with Chiron

Add code
Jan 14, 2025
Figure 1 for Hierarchical Autoscaling for Large Language Model Serving with Chiron
Figure 2 for Hierarchical Autoscaling for Large Language Model Serving with Chiron
Figure 3 for Hierarchical Autoscaling for Large Language Model Serving with Chiron
Figure 4 for Hierarchical Autoscaling for Large Language Model Serving with Chiron
Viaarxiv icon

Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction

Add code
Apr 12, 2024
Viaarxiv icon