IMBPS - Iterative MLP Blocks with Parameter Splits for Improving LLM Inference.
Ganesh Prasad Nagaraja, Arun Ramachandran, Shubhendu Sharma, R. Govindarajan, Prakash Sathyanath Raghavendra
Browse the full HiPC paper archive.
Ganesh Prasad Nagaraja, Arun Ramachandran, Shubhendu Sharma, R. Govindarajan, Prakash Sathyanath Raghavendra
Browse the full HiPC paper archive.