We introduce ExTernD (Expanded-rank Ternary Decomposition), a post-training factorization of each LLM weight matrix $A \in \mathbb{R}^{m \times n}$ into $A \approx B \mathrm{diag}(D) C$ with ternary factors $B \in \{-1,0,+1\}^{m \times k}$, $C \in \{-1,0,+1\}^{k \times n}$ and a real scale vector $D \in \mathbb{R}^k$. The inner rank $k = μ\min(m,n)$ is deliberately expanded beyond full rank ($μ> 1$), so that components past full rank correct the quantization error of earlier ones.
arXiv:2607. 18745v1 Announce Type: new Abstract: We study low-precision computation of C=AB with both factors quantized.
By Piyush Sao, Narasinga Miniskar, Pedro Valero-Lara, Keita Teranishi, Sudip Seal
arXiv:2512. 00956v3 Announce Type: replace Abstract: Quantizing LLM weights and activations is a standard approach for efficient deployment, but a few extreme outliers can stretch the dynamic range and amplify low-bit quantization errors.
By Jiale Chen, Vage Egiazarian, Roberto L. Castro, Torsten Hoefler, Dan Alistarh
arXiv:2608. 14149v1 Announce Type: new Abstract: Recent training-free post-training quantization methods restore model accuracy through closed-form residual compensation.
By Lin-Fa Lee, Yi-Yu Chang, Kuo-Hei Yeh
arXiv:2608. 01091v1 Announce Type: new Abstract: AdaBoost.
By Xin Zou, Jingyuan Xu
arXiv:2608. 08910v1 Announce Type: cross Abstract: PTQTP decomposes LLM weight matrices into two ternary (trit) planes with two free per-group scales.
By Matteo Grella
arXiv:2607. 04302v1 Announce Type: cross Abstract: We present HiFA4, a post-training operator-level design that executes both QK^T and PV in FlashAttention as 4-bit HIF4 Cube GEMMs for LLM inference on Ascend NPUs, while maintaining the online softmax state in FP16.
By Hui Dong, Yanzhao Li, Jie Gao, Chunlu Li, Zhiyuan Zhang, Yupeng Sun, Zhenyuan Chen, Zhiqiang Zou
arXiv:2607. 18343v1 Announce Type: cross Abstract: Federated fine-tuning is bottlenecked by communication: FedAvg and pseudo-gradient schemes transmit a payload that scales with the model, and gradient compression shrinks it by only a constant factor.
By Radhakrishna Achanta, Will Reed
arXiv:2606. 26650v1 Announce Type: cross Abstract: In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs.
By Shigeng Wang, Chao Li, Yangyuxuan Kang, Jiawei Fan, Anbang Yao
arXiv:2606. 26587v1 Announce Type: cross Abstract: Low-bit floating-point formats and semi-structured sparsity are increasingly supported by modern accelerators, yet combining them for LLM activation compression remains challenging: activations contain input-dependent outliers that dominate block scales in FP4 quantization, and directly applying N:M sparsity masks discards moderate values, coupling sparsification loss with quantization error.
By Haoqian Meng, Yilun Luo, Yafei Zhao, Wenyuan Liu, Huaqing Zheng, Xindian Ma, Peng Zhang
arXiv:2606. 06521v1 Announce Type: cross Abstract: FP8 (E4M3) acceleration for attention computation offers significant throughput gains, but the 3-bit mantissa introduces precision challenges when the softmax probability matrix P is cast to FP8 before the P*V matrix multiplication.
By Reed Lau
arXiv:2608. 15567v1 Announce Type: new Abstract: Weight-only post-training quantization (PTQ) enables the deployment of large language models under tight memory budgets, but accuracy often collapses at 2-3 bits.
By Gunjun Lee, Sehwan Son, Younjoo Lee, Byungjun Kim, Jung Ho Ahn