LLM-FP4: 4-Bit Floating-Point Quantized Transformers
Open accessAbstract
We propose LLM-FP4 for quantizing both weights and activations in large language models (LLMs) down to 4-bit floating-point values, in a post-training manner.Existing posttraining quantization (PTQ) solutions are primarily integer-based and struggle with bit widths below 8 bits.Compared to integer quantization, floating-point (FP) quantization is more flexible and can better handle long-tail or bell-shaped distributions, and it has emerged as a default choice in many hardware platforms.One characteristic of FP quantization is that its performance largely depends on the choice of exponent bits and clipping range.In this regard, we construct a strong FP-PTQ baseline by searching for the optimal quantization parameters.Furthermore, we observe a high interchannel variance and low intra-channel variance pattern in activation distributions, which adds activation quantization difficulty.We recognize this pattern to be consistent across a spectrum of transformer models designed for diverse tasks, such as LLMs, BERT, and Vision Transformer models.To tackle this, we propose per-channel activation quantization and show that these additional scaling factors can be reparameterized as exponential biases of weights, incurring a negligible cost.Our method, for the first time, can quantize both weights and activations in the LLaMA-13B to only 4-bit and achieves an average score of 63.1 on the common sense zero-shot reasoning tasks, which is only 5.8 lower than the full-precision model, significantly outperforming the previous stateof-the-art by 12.7 points.Code is available at: https://github.com/nbasyl/LLM-FP4.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
LLM-FP4 proposes a pre-shifted exponent bias method, effective in managing high inter-channel variance often encountered in transformer models, thereby improving precision of activations quantization.
“Additionally, LLM-FP4 proposes an innovative pre-shifted exponent bias method. This method is particularly effective in managing the high inter-channel variance often encountered in transformer models, thereby improving the precision of activations quantization.”
From Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey (2024) · cites this paper as [59]
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · see citing works
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 21,793 · see citing works
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · see citing works
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821 · see citing works
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602 · see citing works
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5446 · Cited by 4,222 · see citing works
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · Cited by 1,749 · see citing works
Data-Free Quantization Through Weight Equalization and Bias Correction
Nagel, M., Baalen, M. V., Blankevoort, T., & Welling, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00141 · Cited by 500 · see citing works
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and TextPreprint
Akbari, H., Yuan, L., Qian, R., Chuang, W.-H., Chang, S., Cui, Y., & Gong, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.11178 · Cited by 433 · see citing works
Low-bit Quantization of Neural Networks for Efficient Inference
Choukroun, Y., Kravchik, E., Yang, F., & Kisilev, P. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00363 · Cited by 404 · see citing works
ZeroQ: A Novel Zero Shot Quantization Framework
Cai, Y., Yao, Z., Dong, Z., Gholami, A., Mahoney, M. W., & Keutzer, K. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01318 · Cited by 381 · see citing works
FP8 Formats for Deep LearningPreprint
Micikevicius, P., Stosic, D., Burgess, N., Cornea, M., Dubey, P., Grisenthwaite, R., Ha, S., Heinecke, A., Judd, P., Kamalu, J., et al. (2022) · arXiv.org · doi:10.48550/arxiv.2209.05433 · Cited by 352 · see citing works
LLM.int8(): 8-Bit Matrix Multiplication for Transformers at Scale
Dettmers, T., Lewis, M., Belkada, Y., & Zettlemoyer, L. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-2198 · Cited by 305 · see citing works
Up or Down? Adaptive Rounding for Post-Training Quantization
Nagel, M., Amjad, R. A., van Baalen, M., Louizos, C., & Blankevoort, T. (2020) · arXiv · doi:10.48550/arxiv.2004.10568 · Cited by 252 · see citing works
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
Xiao, G., Lin, J., Seznec, M., Wu, H., Demouth, J., & Han, S. (2022) · arXiv · doi:10.48550/arxiv.2211.10438 · Cited by 247 · see citing works
Post-Training Quantization for Vision Transformer
Liu, Z., Wang, Y., Han, K., Ma, S., & Gao, W. (2021) · arXiv · doi:10.48550/arxiv.2106.14156 · Cited by 192 · see citing works
Self-citationBRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
Li, Y., Gong, R., Tan, X., Yang, Y., Hu, P., Zhang, Q., Yu, F., Wang, W., & Gu, S. (2021) · arXiv · doi:10.48550/arxiv.2102.05426 · Cited by 190 · see citing works
PTQ4ViT: Post-Training Quantization for Vision Transformers with Twin Uniform Quantization
Yuan, Z., Xue, C., Chen, Y., Wu, Q., & Sun, G. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19775-8_12 · Cited by 163 · cited 7× · see citing works
“…still bur-densome, therefore, we use the diagonal entries of the Fisher Information Matrix of O to substitute ¯ H ( O ) following (Li et al., 2021; Yuan et al., 2022), and the new Hessian-based metric becomes: (24) Here, each entry of O is assumed to be independent and n denoted the total number…”
BackgroundMethodInfluentialUnderstanding and Overcoming the Challenges of Efficient Transformer Quantization
Bondarenko, Y., Nagel, M., & Blankevoort, T. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.627 · Cited by 92 · see citing works
Towards Accurate Post-Training Quantization for Vision Transformer
Ding, Y., Qin, H., Yan, Q., Chai, Z., Liu, J., Wei, X., & Liu, X. (2022) · Proceedings of the 30th ACM International Conference on Multimedia · doi:10.1145/3503161.3547826 · Cited by 79 · see citing works
QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training QuantizationPreprint
Wei, X., Gong, R., Li, Y., Liu, X., & Yu, F. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.05740 · Cited by 69 · see citing works
EasyQuant: Post-training Quantization via Scale Optimization
Wu, D., Tang, Q., Zhao, Y., Zhang, M., Fu, Y., & Zhang, D. (2020) · arXiv · doi:10.48550/arxiv.2006.16669 · Cited by 44 · see citing works
Towards Efficient Post-Training Quantization of Pre-Trained Language Models
Bai, H., Hou, L., Shang, L., Jiang, X., King, I., & Lyu, M. R. (2022) · neural information processing systems · doi:10.52202/068431-0103 · Cited by 31 · see citing works
FP8 Quantization: The Power of the Exponent
Kuzmin, A., van Baalen, M., Ren, Y., Nagel, M., Peters, J. W. T., & Blankevoort, T. (2022) · neural information processing systems · doi:10.52202/068431-1065 · Cited by 24 · see citing works
Lee, J., Kwon, Y., Park, S., Yu, M., Park, J., & Song, H. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3403844 · Cited by 18 · see citing works
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
Liu, Z., Oguz, B., Zhao, C., Chang, E., Stock, P., Mehdad, Y., Shi, Y., Krishnamoorthi, R., & Chandra, V. (2023) · arXiv · doi:10.48550/arxiv.2305.17888 · Cited by 13 · see citing works
Self-citationInteger or Floating Point? New Outlooks for Low-Bit Quantization on Large Language ModelsPreprint
Zhang, Y., Zhao, L., Cao, S., Wang, W., Cao, T., Yang, F., Yang, M., Zhang, S., & Xu, N. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.12356 · Cited by 4 · see citing works
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805
Flagged first, then by citations
1 of the 29 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
A Survey on Model Compression for Large Language Models
Zhu, X., Li, J., Liu, Y., Ma, C., & Wang, W. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00704 · Cited by 273 · see citing works
A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models
Guo, C., Cheng, F., Du, Z., Kiessling, J., Ku, J., Li, S., Li, Z., Ma, M., Molom-Ochir, T., Morris, B., et al. (2025) · IEEE Circuits and Systems Magazine · doi:10.1109/mcas.2024.3476008 · Cited by 32 · see citing works
Cambricon-LLM: A Chiplet-Based Hybrid Architecture for On-Device Inference of 70B LLM
Yu, Z., Liang, S., Ma, T., Cai, Y., Nan, Z., Huang, D., Song, X., Hao, Y., Zhang, J., Zhi, T., et al. (2024) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro61859.2024.00108 · Cited by 31 · see citing works
Decentralized Generative AI Model Deployment Using Microservices
Jhingran, S., Bansal, N., Chaturvedi, R., Singh, A., & Arora, Y. (2024) · International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA) · doi:10.1109/icaiqsa64000.2024.10882424 · Cited by 18 · see citing works
AiF: Accelerating On-Device LLM Inference Using In-Flash Processing
Lee, J., Kim, H., Oh, S., Chun, M., Kim, M., & Kim, J. (2025) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1145/3695053.3731073 · Cited by 18 · see citing works
Energy-Efficient Transformer Inference: Optimization Strategies for Time Series Classification
Kermani, A., Zeraatkar, E., & Irani, H. (2025) · International Journal of Computer Applications · doi:10.5120/ijca2025924771 · Cited by 14 · see citing works
A survey of low-bit large language models: Basics, systems, and algorithms
Gong, R., Ding, Y., Wang, Z., Lv, C., Zheng, X., Du, J., Yong, Y., Gu, S., Qin, H., Guo, J., et al. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107856 · Cited by 16 · see citing works
SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving
Li, X., Spatharakis, D., Ghafouri, S., Fan, J., Vandierendonck, H., John, D., Ji, B., & Nikolopoulos, D. S. (2025) · ACM/IEEE Symposium on Edge Computing (SEC) · doi:10.1145/3769102.3770608 · Cited by 11 · see citing works
Survey on Efficient Large Language Models: Principles, Algorithms, Applications, and Open Issues
Cheng, J., Kang, H., Shao, Y., Li, N., Chen, P., Wang, R., Long, S., Yang, X., & Ma, L. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3628671 · Cited by 11 · see citing works
MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving
Lee, J., Park, J., Cha, S., Cho, J. H., & Sim, J. (2025) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1145/3725843.3756118 · Cited by 9 · see citing works
Addressing Activation Outliers in LLMs: A Systematic Review of Post-Training Quantization Techniques
Czakó, P., Kertész, G., & Szénási, S. (2025) · IEEE Access · doi:10.1109/access.2025.3568702 · Cited by 7 · see citing works
Gustrowsky, B., Villarreal, J. L., & Alférez, G. H. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-66336-9_19 · Cited by 7 · see citing works
LLM.265: Video Codecs Are Secretly Tensor Codecs
Xu, C., Wu, Y., Yang, X., Chen, B., Lentz, M., Zhuo, D., & Wills, L. W. (2025) · IEEE Micro · doi:10.1109/mm.2026.3701735 · Cited by 6 · see citing works
A Microscaling Multi-Mode Gain-Cell Computing-in-Memory Macro for Advanced AI Edge Device
Tien, J.-C., Wu, P.-C., Khwa, W.-S., Lele, A. S., Su, J.-W., Cheng, C.-Y., Hsu, J.-M., Chen, Y.-C., Hsieh, L.-J., Bai, J.-C., et al. (2025) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2025.3617944 · Cited by 5 · see citing works
AxCore: A Quantization-Aware Approximate GEMM Unit for LLM Inference
Zou, J., Chen, Y., Chen, X., Xu, C., & Chen, X. (2025) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1145/3725843.3756094 · Cited by 5 · see citing works
Welsh, M., Lopez-Rippe, J., Alkhulaifat, D., Khalkhali, V., Wang, X., Sinti-Ycochea, M., & Sotardi, S. T. (2025) · Inventions · doi:10.3390/inventions10040055 · Cited by 5 · see citing works
COMET: Towards Practical W4A4KV4 LLMs Serving
Liu, L., Cheng, L., Ren, H., Zhaohui, X., Pan, Y., Wang, M., Li, X., Han, Y., & Wang, Y. (2025) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3676641.3716252 · Cited by 5 · see citing works
Amgpt: A Large Language Model for Contextual Querying in Additive ManufacturingPreprint
Chandrasekhar, A., Chan, J., Ogoke, F., Ajenifujah, O., & Farimani, A. B. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4870552 · Cited by 5 · see citing works
Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey
Du, D., Gong, G., & Chu, X. (2024) · arXiv · doi:10.48550/arxiv.2405.00314 · Cited by 4 · see citing works
“Further delving into the realm of floating-point quantization, LLM-FP4 [59] elaborates on the formulation of floating-point variables and their quantization.”
BackgroundShen, A., Lai, Z., & Zhang, L. (2024) · Applied Sciences · doi:10.3390/app142110025 · Cited by 3 · see citing works
Zhao, Y., Xie, H., Wang, Z., Tian, C., Li, L., Zhu, Y., Martins, R. P., Chan, C., & Zhang, M. (2025) · Custom Integrated Circuits Conference · doi:10.1109/cicc63670.2025.10982833 · Cited by 3 · see citing works
Deep Compression on Segment Anything Model for Efficient Industrial Manufacturing
Zheng, Y., Liu, J., Li, Q., Li, J., & Xi, Z. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3585613 · Cited by 2 · see citing works
Afeefa, P. P., Hazari, R., & Das, P. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78119-3_12 · Cited by 2 · see citing works
Progtuning: Progressive Fine-Tuning Framework for Transformer-Based Language Models
Ji, X., Zhao, Z., Chen, X., Zhao, X., & Liu, Z. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-6599-0_21 · Cited by 1 · see citing works
Self-citationFP2: A 2-bit Floating-Point Format for Edge-AI Inference and Fine-Tuning
Dang, Q., Ma, C., Huang, H., Fu, G., Huo, Z., Yang, G., Zong, P., Xia, T., Zhao, W., & Ren, P. (2025) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2025.3638831 · Cited by 1 · see citing works
Chen, Y., Gao, H., Lin, Y., & Shi, C. (2026) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ae379b · Cited by 1 · see citing works
Challenges and Trends of SRAM based Floating Point Computing-in-Memory Circuits
Tang, Y., Zhang, Y., Liu, Z., Wang, X., Wu, D., Zhang, H., Sun, Y., & Si, X. (2025) · IEEE International Conference on ASIC (ASICON) · doi:10.1109/asicon66040.2025.11326315 · Cited by 1 · see citing works
Self-citationLoCaLUT: Harnessing Capacity–Computation Tradeoffs for LUT-Based Inference in DRAM-PIM
Hong, J., Shin, C., Kim, S., Noh, S. U., Kwon, T., Park, S., Kim, H., Kim, Y., & Lee, J. (2026) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca68181.2026.11408523 · Cited by 1 · see citing works
Feature Map Compression for Split Learning in Mobile Wireless Environment: Theory and Practice
Zhou, W., Qu, Z., Ye, B., Lyu, S.-H., Cai, M., Ji, M., & Guo, S. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3696694 · Cited by 1 · see citing works
BitNet v2: Low-Bit and Sparsified Activations for 1-Bit Large Language Models
Wang, H., Ma, S., & Wei, F. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3717905 · Cited by 1 · see citing works
Borgianni, L., Ottella, M., Heer, R., Montiel-Nelson, J. A., Pau, D. P., Proietti, R., Schotter, J., & Tarvainen, M. P. (2025) · Smart Systems Integration Conference and Exhibition (SSI) · doi:10.1109/ssi65953.2025.11107204 · Cited by 1 · see citing works
Searching Optimal Floating-Point Format for Sub-8-Bit Large Language Model Inference
Hwang, Y., Lee, J., Park, J., Lim, J., & Choi, J. (2024) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.1109/iceic61013.2024.10457111
LEP: Leveraging Local Entropy Pruning for Sparsity in Large Language Models
Chen, Y., Cheng, B. C., Zhang, Y., Zhang, S., Wu, Z., & Meng, F. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888911
SDM-M-DID: Self-decoding model for medical de-identification
Budiakov, B., Liu, T., Chen, J., & Karev, A. (2025) · Intelligent Data Analysis · doi:10.1177/1088467x251332846
LLM Training Workload IO Characteristics
Gunnam, K., Mohandas, A., Dhote, M. K., Bhagwat, R., Darshan, P., & Kothalikar, K. (2025) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas56072.2025.11044158
Quantization of Hindi LLM to various bit precisions using HQQ
Akshat, A., Tripathi, K., Malik, D., & Lata, K. (2025) · AIP conference proceedings · doi:10.1063/5.0289586
XShift: FPGA-efficient Binarized LLM with Joint Quantization and Sparsification
Zhou, S., Tian, H., Meng, S., Chen, J., Yu, J., & Wang, K. (2025) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac63849.2025.11133363
Thinking Fast and Correct: Automated Rewriting of Numerical Code through Compiler Augmentation
Qian, S., Sathia, V., Ivanov, I. R., Hückelheim, J., Hovland, P., & Moses, W. S. (2026) · Proceedings of the CGO/Proceedings of the ... CGO · doi:10.1109/cgo68049.2026.11395228
DayPQ: Dynamic Layerwise Pruning and Quantization for LLM Inference Acceleration
Xu, Y., Li, M., Zhuo, Z., Zhi, Q., Jia, T., & Wang, M. (2026) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2026.3666193
Efficient Adaptation of Vietnamese Large Language Models for Sentiment Analysis
Bui, V.-T., Nguyen, V.-V., & Nguyen, P.-T. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-21625-0_11
Hybrid LLM Architectures for On-Device and Cloud-Based Intelligence in Regulated Industries
Koduri, S. K. A. (2026) · IEEE SoutheastCon · doi:10.1109/southeastcon63549.2026.11476177
Meng, Q., Hu, J. B., Zhang, Z., Li, Z. L., Shi, X., Luo, J., Huang, Q. C., Wang, H., & Chang, S. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3696603
Comparative Evaluation of Modern Large Language Models for Nepali Language Generation
Shrestha, N., & Ghimire, S. K. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-22292-3_8
Yu, Y., Qiang, X., Che, J., Wen, W., Lan, Q., Smith, A., & Qiang, Y. (2026) · ICON · doi:10.1109/icnlp69856.2026.11527597
Zhao, L., Shao, K., Liao, Z., Huang, X., Cheng, K.-T. T., Tsui, C.-Y., & Zou, Y. (2026) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2026.3693970
Self-citationGeng, X., Liu, S., Wang, H., Han, J., & Jiang, H. (2026) · Design, Automation, and Test in Europe · doi:10.23919/date69613.2026.11539270
Self-citationShao, K., Zhao, L., Yu, J., Liao, Z., Wang, X., Zou, Y., Cheng, K.-T. T., & Tsui, C.-Y. (2026) · Design, Automation, and Test in Europe · doi:10.23919/date69613.2026.11539592
Self-citationHessian-Aware Zeroth-Order Optimization for Quantized Large Language Models
Wang, Z., Wu, Y., Huang, Y., Cheng, P., Guo, Q., & Tang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3394-6_33
UniCore: A Bit-Width Scalable GEMM Unit for Unified LLM Inference
Chen, Y., Zou, J., Chen, X., Xu, C., Guo, J., & Chen, X. (2026) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca66397.2026.00176
MXFFP: Microscaling Flexible Floating Point Format for Large-Scale AI Model Acceleration
Kim, S., Kim, S., Ha, D., Lee, H., KIM, J., Lee, S., Jung, M., Annavaram, M., & Ro, W. W. (2026) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca66397.2026.00175
Fold-FP4: Folding for Energy Efficient FP4 Matrix Multiplication
Fang, Q., Wang, Y., Zhao, Y., Chen, Y., & Guo, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-4805-6_22
- Authors
- Liu, S.-Y., Liu, Z., Huang, X., Dong, P., & Cheng, K.-T.
- Affiliations
- Hong Kong University of Science and Technology (HK)
- Meta (United States) (US)
- Venue
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Published
- 2023
- Pages
- 592-605
- OpenAlex
- W4389519530
- Cited by
- 50
- References
- 29
- Citations by year
- 2026: 18 · 2025: 24 · 2024: 8
- FWCI
- 5.35
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China
- Hong Kong University of Science and Technology
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Numerical Methods and Algorithms
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- floating-point quantization, post-training quantization, large language models, 4-bit quantization, weight quantization, activation quantization, zero-shot reasoning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
