BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
Paper • 2402.04291 • Published • 50
quantization
-
-
OneBit: Towards Extremely Low-bit Large Language Models
Paper • 2402.11295 • Published • 24 -
A Survey on Transformer Compression
Paper • 2402.05964 • Published • 1 -
Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers
Paper • 2402.08958 • Published • 5 -
BitDelta: Your Fine-Tune May Only Be Worth One Bit
Paper • 2402.10193 • Published • 21 -
GPTVQ: The Blessing of Dimensionality for LLM Quantization
Paper • 2402.15319 • Published • 22 -
EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs
Paper • 2403.02775 • Published • 13 -
4-bit Shampoo for Memory-Efficient Network Training
Paper • 2405.18144 • Published • 12 -
PrefixQuant: Static Quantization Beats Dynamic through Prefixed Outliers in LLMs
Paper • 2410.05265 • Published • 33 -
BitNet a4.8: 4-bit Activations for 1-bit LLMs
Paper • 2411.04965 • Published • 70 -
"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization
Paper • 2411.02355 • Published • 52 -
NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks
Paper • 2410.20650 • Published • 17 -
BitStack: Fine-Grained Size Control for Compressed Large Language Models in Variable Memory Environments
Paper • 2410.23918 • Published • 21 -
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
Paper • 2607.05147 • Published • 19