The paper introduces FAMPWQ, a Fisher information-based Adaptive Mixed Precision Weight Quantization method designed to improve Large Language Model inference on commodity GPUs. It uses a Fisher information metric to assess layer-wise sensitivity and a reinforcement learning-based bit-width allocator to adaptively assign precision per layer. Experiments across seven models and five benchmarks show significant gains in perplexity, accuracy, and LLM-as-a-judge performance compared to seven baseline approaches.
arXiv:2605. 26660v2 Announce Type: replace Abstract: Quantization is an effective approach to reduce the memory footprint and inference cost of large language models (LLMs), yet maintaining performance in the ultra-low-bit regime remains challenging.
arXiv:2607. 23047v1 Announce Type: cross Abstract: Mixed-precision quantization improves the accuracy of post-training quantization by allocating higher bitwidths to sensitive layers, but existing methods solve the allocation for a single fixed memory budget.
arXiv:2605. 08692v2 Announce Type: replace Abstract: Post-training weight-only quantization to 4 bits is widely used to reduce the memory and compute costs of large language model inference.
arXiv:2410. 13056v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable success across a wide range of language tasks, but their deployment on edge devices remains challenging due to the substantial memory requirements imposed by their large parameter sizes.
Squeeze10-LLM is a staged mixed‑precision post‑training quantization framework that reduces 16‑bit LLM weights to an average of 1.6 bits per weight by assigning 80% of weights to 1 bit and 20% to 4 bits. It introduces Post‑Binarization Activation Robustness (PBAR), a weight significance metric that considers activation impact, and Full Information Activation Supervision (FIAS), a strategy that preserves activation information to limit error propagation. Experiments on LLaMA and LLaMA2 demonstrate that Squeeze10‑LLM achieves state‑of‑the‑art performance for sub‑2‑bit weight‑only quantization, raising average accuracy from 43% to 56% on six zero‑shot classification tasks.
arXiv:2602. 10431v4 Announce Type: replace Abstract: Large language models (LLMs) demand substantial computational and memory resources, posing challenges for efficient deployment.
arXiv:2606. 04115v1 Announce Type: cross Abstract: Quantizing large language models (LLMs) to low-precision floating-point representations is central to efficient deployment, yet applying a single bit-width uniformly across all layers is sub-optimal in terms of both performance and accuracy.
arXiv:2606. 13054v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit exceptional general language processing capabilities, but their memory and compute costs hinder deployment.
arXiv:2604. 25421v2 Announce Type: replace-cross Abstract: Federated fine-tuning provides a practical route to adapt large language models (LLMs) on edge devices without centralizing private data, yet in mobile deployments the training wall-clock is often bottlenecked by straggler-limited uplink communication under heterogeneous bandwidth and intermittent participation.
arXiv:2602. 01027v2 Announce Type: replace Abstract: Mixed-precision quantization is a promising approach for compressing large language models under tight memory budgets.
Large language models (LLMs) exhibit exceptional general language processing capabilities, but their memory and compute costs hinder deployment. Ternarization has emerged as a promising compression technique, offering significant reductions in model size and inference complexity.
arXiv:2606. 10531v1 Announce Type: cross Abstract: Quantization-aware training (QAT) is essential for extremely low-bit large language models (LLMs).