arXiv AI
Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 16
Channel-Wise and Token-Aware Post-Training Quantization for Visual State Space Duality
arXiv:2609.16656v1 Announce Type: new Abstract: State space models (SSMs), particularly Mamba, have emerged as efficient alternatives to attention-based architectures and have been extended to vision...
arXiv AI
Oct 7
Test-Time Adaptation of Quantized ViTs via Single-Pass Quantizer-Aligned Recalibration
The paper introduces Quantizer‑Aligned Recalibration (QuAR), a single‑pass test‑time adaptation technique for quantized vision transformers that does not require backpropagation or parameter updates. QuAR recalibrates activations at the input of frozen quantizers by aligning per‑channel statistics with the source calibration, thereby correcting the distorted code distribution caused by distribution shift. On ImageNet‑C, QuAR outperforms state‑of‑the‑art backprop‑free methods across 3‑, 4‑, 6‑, and 8‑bit precisions, achieving higher accuracy, lower latency, and minimal memory overhead while maintaining performance across diverse shift scenarios.
arXiv AI
Oct 12
DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs
DualQuant introduces a dual‑scale, calibration‑free post‑training quantization framework that jointly optimizes weight‑reconstruction MSE and derives per‑channel activation rescalings, enabling effective 4‑bit weight and activation quantization without calibration data. The method employs a non‑differentiable optimization solved via variable splitting and block coordinate descent, supporting a wide range of formats including MX and NVFP4. Experiments on Llama and Qwen models show DualQuant matches or surpasses calibration‑based SmoothQuant and significantly outperforms other calibration‑free baselines, achieving up to 2.61× memory reduction and 2.46× throughput speedup on an RTX 4090.
arXiv AI
Oct 15
LoopQuant: Accurate and Efficient Post-Training Quantization for Looped Transformers
arXiv:2610.16368v1 Announce Type: cross Abstract: Looped Language Models (LoopLMs) improve parameter efficiency by recursively reusing shared Transformer modules, yet their repeated computation over...
Hugging Face Trending Papers
Sep 15
Channel-Wise and Token-Aware Post-Training Quantization for Visual State Space Duality
State space models (SSMs), particularly Mamba, have emerged as efficient alternatives to attention-based architectures and have been extended to vision through ViM, VMamba, and Visual State Space Dual...
arXiv Computation and Language
2d ago
MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM
MoBiQuant introduces a Mixture-of-Bits quantization framework that allows large language models to be inferred at varying precisions during runtime. It addresses the poor generalization of existing post‑training quantization methods by mitigating precision‑dependent outlier migration through a recursive residual quantization scheme and a token‑aware router that selects the optimal precision per token. Experiments demonstrate that MoBiQuant matches or exceeds single‑precision PTQ performance while providing significant memory savings and up to 1.34× throughput gains over current any‑precision approaches.