2 papers
cs.LG2026
TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation
Junhan Kim, Yeo Jeong Park, Seungwoo Son +4
The rapid growth of large language models (LLMs) has heightened the importance of post-training quantization (PTQ) for reducing memory and computation costs. Among PTQ methods, GPT…
cs.LG2024
Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers
Junhan Kim, Chungman Lee, Eulrang Cho +4
With the increasing complexity of generative AI models, post-training quantization (PTQ) has emerged as a promising solution for deploying hyper-scale models on edge devices such a…