6 citations · 13 across the 8 of their papers we have counts for
7 papers · 1 filter
Dual-QK: Sharp Queries and Flat Keys for Prunable 2-bit KV Caches
Sunjoo Whang, Jungjun Oh, Minsung Kim +5
Long inputs and extended generation increase the storage and access costs of the key-value (KV) cache. Low-bit quantization reduces storage and memory traffic, while query-channel…
EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding
Sangwoo Ha, Hyunwoo Seo, Yurim Jo +2
On-device deployment of Large Language Models (LLMs) has become essential for personalized edge applications. A primary bottleneck is external memory access (EMA) in feed-forward n…
LightRot: A Light-Weighted Rotation Scheme and Architecture for Accurate Low-Bit Large Language Model Inference
Sangjin Kim, Yuseon Choi, Jungjun Oh +2
As large language models (LLMs) continue to demonstrate exceptional capabilities across various domains, the challenge of achieving energy-efficient and accurate inference becomes…
GyRot: Leveraging Hidden Synergy between Rotation and Fine-grained Group Quantization for Low-bit LLM Inference
Sangjin Kim, Yuseon Choi, Byeongcheol Kim +2
Low-bit quantization is essential for efficient LLM inference, and both rotation and fine-grained group quantization have shown individual promise. However, their combination often…
ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving
Yuseon Choi, Jingu Lee, Jungjun Oh +5
Mixture-of-Experts (MoE) models have become the dominant architecture for large-scale language models, yet on-premises serving remains fundamentally memory-bound as batching turns…
FlashMoE: Reducing SSD I/O Bottlenecks via ML-Based Cache Replacement for Mixture-of-Experts Inference on Edge Devices
Byeongju Kim, Jungwan Lee, Donghyeon Han +2
Recently, Mixture-of-Experts (MoE) models have gained attention for efficiently scaling large language models. Although these models are extremely large, their sparse activation en…
SeVeDo: A Heterogeneous Transformer Accelerator for Low-Bit Inference via Hierarchical Group Quantization and SVD-Guided Mixed Precision
Yuseon Choi, Sangjin Kim, Jungjun Oh +2
Low-bit quantization is a promising technique for efficient transformer inference by reducing computational and memory overhead. However, aggressive bitwidth reduction remains chal…