65 citations · 90 across the 7 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
MXCode: Vector Quantization for MX-Native Inference at Scale
Gaurav Kolhe, Cansu Demirkiran, Shubhi Tyagi +8
Memory capacity and bandwidth are major bottlenecks in LLM inference, motivating weight compression beyond conventional 4-bit quantization. Vector quantization (VQ) enables approxi…
cs.LG2025
Systolic Array-based Accelerator for Structured State-Space Models
Shiva Raja, Cansu Demirkiran, Aakash Sarkar +2
Sequence modeling is crucial for AI to understand temporal data and detect complex time-dependent patterns. While recurrent neural networks (RNNs), convolutional neural networks (C…