activity
20242026
collaborators

8 papers

cs.LG2026

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving

Hanjiang Wu, Abhimanyu Rajeshkumar Bambhaniya, Sarbartha Banerjee +9

Modern large language model (LLM) inference has progressively disaggregated to keep pace with growing model sizes and tight TTFT and TPOT service-level objectives: from chunked-pre…

cs.LG2025

OPTIMA: Optimal One-shot Pruning for LLMs via Quadratic Programming Reconstruction

Mohammad Mozaffari, Samuel Kushnir, Maryam Mehri Dehnavi +1

Post-training model pruning is a promising solution, yet it faces a trade-off: simple heuristics that zero weights are fast but degrade accuracy, while principled joint optimizatio…

cs.LG2025

SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression

Mohammad Mozaffari, Amir Yazdanbakhsh, Maryam Mehri Dehnavi

Conventional model compression techniques for LLMs address high memory consumption and slow inference challenges but typically require computationally expensive retraining to prese…

cs.LG2025

SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity

Samir Khaki, Xiuyu Li, Junxian Guo +7

Fine-tuning LLMs is both computationally and memory-intensive. While parameter-efficient fine-tuning methods, such as QLoRA and DoRA, reduce the number of trainable parameters and…

cs.AR2025

Beyond Moore's Law: Harnessing the Redshift of Generative AI with Effective Hardware-Software Co-Design

Amir Yazdanbakhsh

For decades, Moore's Law has served as a steadfast pillar in computer architecture and system design, promoting a clear abstraction between hardware and software. This traditional…

cs.LG2025

SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs

Mohammad Mozaffari, Amir Yazdanbakhsh, Zhao Zhang +1

We propose SLoPe, a Double-Pruned Sparse Plus Lazy Low-rank Adapter Pretraining method for LLMs that improves the accuracy of sparse LLMs while accelerating their pretraining and i…