most citedSambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts

33 citations · 33 across the 2 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2024

Kernel Looping: Eliminating Synchronization Boundaries for Peak Inference Performance

David Koeplinger, Darshan Gandhi, Pushkar Nandkar +9

Token generation speed is critical to power the next wave of AI inference applications. GPUs significantly underperform during token generation due to synchronization overheads at…