Characterizing Training Performance and Energy for Foundation Models and Image Classifiers on Multi-Instance GPUsConnor EspenshadeRachel Penget al.2024EuroMLSys 2024
Towards Pareto Optimal Throughput in Small Language Model ServingPol G. RecasensYue Zhuet al.2024EuroMLSys 2024
Reducing Datacenter Compute Carbon Footprint by Harnessing the Power of Specialization: Principles, Metrics, Challenges and OpportunitiesTamar EilamPradip Boseet al.2024IEEE Trans Semicond Manuf