One Queue Is All You Need: Resolving Head-of-Line Blocking in Large Language Model Serving von Patke, Archit, Reddy, Dhemath, Jha, Saurabh, Qiu, Haoran, Pinto, Christian, Cui, Shengkun, Narayanaswami, Chandra, Kalbarczyk, Zbigniew, Iyer, Ravishankar

Volltext bestellen

Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction von Qiu, Haoran, Mao, Weichao, Patke, Archit, Cui, Shengkun, Jha, Saurabh, Wang, Chen, Franke, Hubertus, Kalbarczyk, Zbigniew T, Başar, Tamer, Iyer, Ravishankar K

Volltext bestellen

Application-aware Congestion Mitigation for High-Performance Computing Systems von Patke, Archit, Jha, Saurabh, Qiu, Haoran, Brandt, Jim, Gentile, Ann, Greenseid, Joe, Kalbarczyk, Zbigniew, Iyer, Ravishankar

Volltext bestellen

DETERMINING OPTIMAL DATA ACCESS FOR DEEP LEARNING APPLICATIONS ON A CLUSTER von Patke, Archit, Gkoufas, Ioannis, Pinto, Christian, Koutsovasilis, Panagiotis, Venugopal, Srikumar

Volltext bestellen

One Queue Is All You Need: Resolving Head-of-Line Blocking in Large Language Model Serving von Patke, Archit, Reddy, Dhemath, Jha, Saurabh, Qiu, Haoran, Pinto, Christian, Cui, Shengkun, Narayanaswami, Chandra, Kalbarczyk, Zbigniew, Iyer, Ravishankar

Volltext

Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction von Qiu, Haoran, Mao, Weichao, Patke, Archit, Cui, Shengkun, Jha, Saurabh, Wang, Chen, Franke, Hubertus, Kalbarczyk, Zbigniew T, Başar, Tamer, Iyer, Ravishankar K

Volltext

A Study of Network Congestion in Two Supercomputing High-Speed Interconnects von Jha, Saurabh, Patke, Archit, Brandt, Jim, Gentile, Ann, Showerman, Mike, Roman, Eric, Kalbarczyk, Zbigniew T, Kramer, William T, Iyer, Ravishankar K

Volltext bestellen

Application-aware Congestion Mitigation for High-Performance Computing Systems von Patke, Archit, Jha, Saurabh, Qiu, Haoran, Brandt, Jim, Gentile, Ann, Greenseid, Joe, Kalbarczyk, Zbigniew, Iyer, Ravishankar

Volltext

A Study of Network Congestion in Two Supercomputing High-Speed Interconnects von Jha, Saurabh, Patke, Archit, Brandt, Jim, Gentile, Ann, Showerman, Mike, Roman, Eric, Kalbarczyk, Zbigniew T, Kramer, William T, Iyer, Ravishankar K

Volltext