activity
20242026
collaborators

9 papers

cs.DC2026

When Does Disaggregation Pay? Simulating Prefill--Decode--Attention--FFN Specialization for Agentic LLM Inference

Przemyslaw Forys, Haoran Wu, Can Xiao +8

Agentic inference now dominates the LLM inference landscape, requiring LLMs to actively engage in multi-turn interactions with tool-calling capabilities. This introduces a more com…

cs.AR2026

CascadeLUT: Information-Ordered Streaming Inference for Bandwidth-Constrained FPGAs

Oliver Cassidy, Marta Andronic, George A. Constantinides

Mapping neural networks to FPGAs enables low-latency, energy-efficient inference, particularly for lookup table (LUT)-based models that eliminate multipliers and map directly to re…

cs.LG2026

Direction-Preserving Number Representations

Bardia Zadeh, George A. Constantinides

Low-precision number formats are widely used in modern machine learning systems due to their efficiency. Accurate direction representation is key to the accuracy of vector operatio…

cs.LG2025

Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding

Taowen Liu, Marta Andronic, Deniz Gündüz +1

LLM training is resource-intensive. Quantized training improves computational and memory efficiency but introduces quantization noise, which can hinder convergence and degrade mode…

cs.LG2025

NeuraLUT-Assemble: Hardware-aware Assembling of Sub-Neural Networks for Efficient LUT Inference

Marta Andronic, George A. Constantinides

Efficient neural networks (NNs) leveraging lookup tables (LUTs) have demonstrated significant potential for emerging AI applications, particularly when deployed on field-programmab…

cs.AR2025

Banked Memories for Soft SIMT Processors

Martin Langhammer, George A. Constantinides

Recent advances in soft GPGPU architectures have shown that a small (<10K LUT), high performance (770 MHz) processor is possible in modern FPGAs. In this paper we architect and eva…