← Search

Safeen Huda

2 accepted papers

2026

HALO: Hardware-Aware Quantization with Low Critical-Path-Delay Weights for LLM Acceleration

AAAI 2026technical

Quantization is critical for efficiently deploying large language models (LLMs). Yet conventional methods remain hardware-agnostic, limited to bit-width constraints, and do not account for intrinsic circuit characteristics such as the timing behaviors and energy profiles of Multiply-Accumulate (MAC)

Cited by 0SourcePDFScholar
2024

ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models

EMNLP 2024main

The high power consumption and latency-sensitive deployments of large language models (LLMs) have motivated efficiency techniques like quantization and sparsity. Contextual sparsity, where the sparsity pattern is input-dependent, is crucial in LLMs because the permanent removal of attention heads or…