method · first seen 5 Oct 2026
mixed-precision quantization
Compressing a neural network by assigning different bit-widths to different modules to balance accuracy and size.
Mentions per week
PapersCodeDiscussion
Earliest sources
- AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM GenerationPapers · 5 Oct 2026 · Hanzhi Zhang, Qiao Zhang, Qinglei Cao, Heng Fan, Yan Huang, Kewei Sha, Yunhe Fen…
- Quantize by Drift: Label-Free Mixed-Precision Post-Training Quantization for Text EmbeddersPapers · 6 Oct 2026 · Hyojung Han, Jongmin Kim, Seung-Hun Jeon
- RAMP: Recurrent Adaptive Mixed Precision for Efficient Prefill in Recurrent-Depth Language ModelsPapers · 9 Oct 2026 · Ke Wan, Chen Chen
- DuoRate: Two-Rate Per-Expert Precision Allocation for Mixture-of-Experts ServingPapers · 9 Oct 2026 · Mengqi Guo, Zhe Wei, Yuan Yuan, Jiunn Bin Lim, Boyi Pan, Michael Bi Mi
- The Price of Precision: A Calibrated Cost Model for Mixed-Precision LLM ServingPapers · 11 Oct 2026 · Mukund Athmaram, Manoj Rao, Liang Ma
- Context-Aware Precision Scheduling for Small Language ModelsPapers · 11 Oct 2026 · Mukund Athmaram, Manoj Rao, Liang Ma
Latest sources
- Joint Quantization and Dynamic Partitioning for Context-Aware Edge Vision TransformersPapers · 10 Nov 2026 · Zhu Jiaqi, Jain Prakriti, Katare Dewant, Kumar Saurabh
- AutoEMatic: Runtime-Adaptive Mixed-Precision LLM Inference via Automatic Exponent-Mantissa RefinementPapers · 6 Nov 2026 · Akshat Ramachandran, Reena Elangovan, Rangharajan Venkatesan, Charbel Sakr, Tijm…
- Coordinated Mixed-Precision KV Cache Quantization for Efficient LLM-based Multi-agent SystemsPapers · 6 Nov 2026 · Weizhong Huang, Jinchao Zhang, Xiawu Zheng
- ACSeL: Adaptive Configuration Search for Hardware-Constrained LLM InferencePapers · 5 Nov 2026 · Bokun Wang, Hung-Yueh Chiang, Diana Marculescu
- TriAttention: Unified Sparse Mixed-Precision Attention for Long-Context LLM InferencePapers · 5 Nov 2026 · Hanzhi Zhang, Qiao Zhang, Qinglei Cao, Heng Fan, Yan Huang, Kewei Sha, Yunhe Fen…
- TileQuant: Tile as the Precision-Allocation Unit for LLM Mixed-Precision Post-Training QuantizationPapers · 4 Nov 2026 · Hanzhi Zhang, Qiao Zhang, Qinglei Cao, Heng Fan, Yan Huang, Kewei Sha, Yunhe Fen…
- MatMoE: Matryoshka Mixture-of-Experts with Dynamic Mixed-Precision Quantization for Efficient InferencePapers · 1 Nov 2026 · Renjie Wei, Haochen Huang, Chuyu Qiu, Jinqi Wen, Dehao Xu, Meng Li
- Low-Bit GDN Recurrent-State Quantization: Global Gradient-aware Allocation and Pure-Write Sliding WindowsPapers · 29 Oct 2026 · Qinghang Huang, Xuchu Huang, Xunzhao Yin
- Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language ModelsPapers · 22 Oct 2026 · Ofek Avivi, Eliron Rahimi, Avi Mendelson, Chaim Baskin
- ProQuant: Preserving Expert Quality over Quantity in Ultra-Low-Bit Quantization of Mixture-of-Experts ModelsPapers · 22 Oct 2026 · Jiaqi Chen, Xianglong Yan, Chengzhu Bao, Xie Chen, Yulun Zhang
- FIGFLEX: A Mixed-Precision FP-INT GEMM Accelerator Co-Designed with Low-Bit LLM QuantizationPapers · 21 Oct 2026 · Faraz Tahmasebi, Haocheng Xu, Andrew Trauger, Yomal Perera, Zhenyu Tang, Nael Ch…
- Spike-Aware Gradient-Based Mixed-Precision Quantization of Spiking Neural Networks for Vision ApplicationsPapers · 21 Oct 2026 · Rajshekhar Rakshit, Devgokul B., Rakshitha Kalkura, Gopalakrishnan Srinivasan