From the 1 of 7 linked papers with an AI index.
7 papers
Output-Aware Rotation for INT2 KV-Cache Quantization
Vincent-Daniel Yun, Woosang Lim, Minsoo Cheong +4
The key-value (KV) cache has become a major memory and bandwidth bottleneck in long-context large language model inference, making ultra-low-bit quantization increasingly important…
NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache
Donghyun Son, Euntae Choi, Sungjoo Yoo
The paper proposes NSNQuant, a calibration‑free method that uses a double normalization and Hadamard transform to compress the key‑value cache of large language models with low‑bit…
LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss
Euntae Choi, Sumin Song, Sungjoo Yoo
Large reasoning models (LRMs) reach competition-level math and coding accuracy via long autoregressive decoding, making per-token decoding cost a primary deployment concern. Weight…
EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models
Minsoo Cheong, Donghyun Son, Woosang Lim +1
Diffusion-based large language models (dLLMs) rely on bidirectional attention, which prevents lossless KV caching and requires a full forward pass at every denoising step. Existing…
Rotate, Clip, and Partition: Towards W2A4KV4 Quantization by Integrating Rotation and Learnable Non-uniform Quantizer
Euntae Choi, Sumin Song, Woosang Lim +1
We propose Rotate, Clip, and Partition (RCP), a quantization-aware training (QAT) approach that first realizes extreme compression of LLMs with W2A4KV4(2-bit weight, 4-bit activati…
Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free
Euntae Choi, Sumin Song, Woosang Lim +1
Large Language Models (LLMs) face deployment challenges due to high computational costs, and while Post-Training Quantization (PTQ) offers a solution, existing rotation-based metho…