Imagen de Portada

SignRoundV2: Toward Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cheng, Wenhua, Zhang, Weiwei, Guo, Heng, Shen, Haihao, Ma, Zaner
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs
por: Cheng, Wenhua, et al.
Publicado: (2023)

Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens
por: Ouyang, Xu, et al.
Publicado: (2024)

Efficient Post-training Quantization with FP8 Formats
por: Shen, Haihao, et al.
Publicado: (2023)

OneBit: Towards Extremely Low-bit Large Language Models
por: Xu, Yuzhuang, et al.
Publicado: (2024)

What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study
por: Lv, Keyu, et al.
Publicado: (2026)

pQuant: Towards Effective Low-Bit Language Models via Decoupled Linear Quantization-Aware Training
por: Zhang, Wenzheng, et al.
Publicado: (2026)

CLAQ: Pushing the Limits of Low-Bit Post-Training Quantization for LLMs
por: Wang, Haoyu, et al.
Publicado: (2024)

Direct Quantized Training of Language Models with Stochastic Rounding
por: Zhao, Kaiyan, et al.
Publicado: (2024)

Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
por: Zhang, Tianao, et al.
Publicado: (2025)

LittleBit: Ultra Low-Bit Quantization via Latent Factorization
por: Lee, Banseok, et al.
Publicado: (2025)

Low-Rank Quantization-Aware Training for LLMs
por: Bondarenko, Yelysei, et al.
Publicado: (2024)

FrameQuant: Flexible Low-Bit Quantization for Transformers
por: Adepu, Harshavardhan, et al.
Publicado: (2024)

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
por: Huang, Wei, et al.
Publicado: (2024)

More Than Bits: Multi-Envelope Double Binary Factorization for Extreme Quantization
por: Ichikawa, Yuma, et al.
Publicado: (2025)

Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs
por: Lin, Haokun, et al.
Publicado: (2025)

Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning
por: Li, Zhen, et al.
Publicado: (2025)

LQER: Low-Rank Quantization Error Reconstruction for LLMs
por: Zhang, Cheng, et al.
Publicado: (2024)

Fitting Is Not Enough: Smoothness in Extremely Quantized LLMs
por: Xu, Yuzhuang, et al.
Publicado: (2026)

BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache
por: Du, Dayou, et al.
Publicado: (2025)

Mixed-Precision Graph Neural Quantization for Low Bit Large Language Models
por: Liu, Wanlong, et al.
Publicado: (2025)

Can Post-Training Quantization Benefit from an Additional QLoRA Integration?
por: Zhu, Xiliang, et al.
Publicado: (2025)

HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs
por: Wang, Guoan, et al.
Publicado: (2026)

XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression
por: Yang, Haoqi, et al.
Publicado: (2025)

Technical Report: Activation Residual Hessian Quantization (ARHQ) for Low-Bit LLM Quantization
por: Wang, YiFeng, et al.
Publicado: (2026)

AdpQ: A Zero-shot Calibration Free Adaptive Post Training Quantization Method for LLMs
por: Ghaffari, Alireza, et al.
Publicado: (2024)

CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs
por: Xu, Yuzhuang, et al.
Publicado: (2024)

The Uneven Impact of Post-Training Quantization in Machine Translation
por: Marie, Benjamin, et al.
Publicado: (2025)

BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation
por: Du, Dayou, et al.
Publicado: (2024)

I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models
por: Hu, Xing, et al.
Publicado: (2024)

Bi-Mamba: Towards Accurate 1-Bit State Space Models
por: Tang, Shengkun, et al.
Publicado: (2024)

RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations
por: Su, Zunhai, et al.
Publicado: (2025)

EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs
por: Zhang, Yuhao, et al.
Publicado: (2025)

Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap
por: Chen, Tianlang, et al.
Publicado: (2026)

Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision
por: Huang, Xijie, et al.
Publicado: (2023)

LLMs for Extremely Low-Resource Finno-Ugric Languages
por: Purason, Taido, et al.
Publicado: (2024)

Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models
por: Park, Jungwoo, et al.
Publicado: (2025)

Revisiting Adaptive Rounding with Vectorized Reparameterization for LLM Quantization
por: Zhou, Yuli, et al.
Publicado: (2026)

QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts
por: Li, Pingzhi, et al.
Publicado: (2024)

Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding
por: Liu, Taowen, et al.
Publicado: (2025)

VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization
por: Yao, Dingyu, et al.
Publicado: (2025)