3 papers
cs.DC2026
SiFAR: Synchronization-Free All-Reduce for Low-Latency LLM Inference
Hritvik Taneja, Anish Saxena, Abhishek Revinipati +3
The rise of reasoning models and agentic systems has made LLM token-generation latency a key bottleneck. Unlike chatbots, whose latency gains saturate at human reading speed, these…
cs.AR2026
TileLens: Efficiently Using Large-Granularity Memory Systems with Transparent Two-Dimensional Memory Layout
Jae Hyung Ju, Euijun Chung, Hritvik Taneja +4
Large Language Model (LLM) inference is bottlenecked by the capacity and bandwidth of GPU High-Bandwidth Memory (HBM). Recent proposals, such as High-Bandwidth Flash (HBF) and RoMe…
cs.DC2025
Utility-Driven Speculative Decoding for Mixture-of-Experts
Anish Saxena, Po-An Tsai, Hritvik Taneja +2
GPU memory bandwidth is the main bottleneck for low-latency Large Language Model (LLM) inference. Speculative decoding leverages idle GPU compute by using a lightweight drafter to…