4 papers · 1 filter
FairyFuse: Multiplication-Free LLM Inference on CPUs via Fused Ternary Kernels
Fei Zuo, Xiaoyan Xi, Quanyi Zeng +2
Large language models are increasingly deployed on CPU-only platforms where memory bandwidth is the primary bottleneck for autoregressive generation. Weight quantization to four bi…
Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in
Feiyu Wang, Xinyu Tan, Bokai Huang +4
Large language models (LLMs) have revolutionized artificial intelligence, yet their massive memory and computational demands necessitate aggressive quantization, increasingly pushi…
HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs
Guoan Wang, Feiyu Wang, Zongwei Lv +2
As large language models (LLMs) continue to scale, deployment is increasingly bottlenecked by the memory wall, motivating a shift toward extremely low-bit quantization. However, mo…
iFairy: the First 2-bit Complex LLM with All Parameters in
Feiyu Wang, Guoan Wang, Yihao Zhang +7
Quantization-Aware Training (QAT) integrates quantization into the training loop, enabling LLMs to learn robust low-bit representations, and is widely recognized as one of the most…