3 papers
cs.LG2026
Quad Length Codes for Lossless Compression of e4m3
Aditya Agrawal, Albert Magyar, Hiteshwar Eswaraiah +5
Training and serving Large Language Models (LLMs) relies heavily on parallelization and collective operations, which are frequently bottlenecked by network bandwidth. Lossless comp…
cs.LG2026
Single-Stage Huffman Encoder for ML Compression
Aditya Agrawal, Albert Magyar, Hiteshwar Eswaraiah +5
Training and serving Large Language Models (LLMs) require partitioning data across multiple accelerators, where collective operations are frequently bottlenecked by network bandwid…
cs.DC2019
High Performance Scalable FPGA Accelerator for Deep Neural Networks
Sudarshan Srinivasan, Pradeep Janedula, Saurabh Dhoble +7
Low-precision is the first order knob for achieving higher Artificial Intelligence Operations (AI-TOPS). However the algorithmic space for sub-8-bit precision compute is diverse, w…