arXiv:2602. 10431v4 Announce Type: replace Abstract: Large language models (LLMs) demand substantial computational and memory resources, posing challenges for efficient deployment.
arXiv:2602. 05367v3 Announce Type: replace Abstract: Efficient deployment of large language models (LLMs) requires extreme quantization, forcing a critical trade-off between low-bit efficiency and performance.
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:2606. 07819v1 Announce Type: new Abstract: Recently, the efficiency of Large Language Models (LLMs) deployment has become a critical concern in practical applications.
The paper presents a target‑centric survey of Quantization‑Aware Training (QAT), a technique that simulates quantization during model training to produce low‑bit models with accuracy comparable to full‑precision ones. It systematically reviews existing QAT methods using a target‑centric taxonomy, highlighting differences in error characteristics, numerical formats, and strategy transferability across targets. The survey also summarizes QAT evaluation paradigms, discusses optimization and deployment challenges, and outlines potential future research directions.
arXiv:2606. 11244v1 Announce Type: cross Abstract: Efficient large language model (LLM) serving is increasingly constrained by deployment cost.
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.
SpecQuant is a training‑free framework that merges speculative decoding with multi‑parent quantization to enable adaptive, efficient inference of large language models. It generates several quantized variants (INT4, FP8, FP16) from a single base model and routes queries to the appropriate variant based on predicted complexity, using lightweight models for simple tasks and full‑precision models for complex reasoning. Evaluations on Qwen2.5 models across MMLU, AlpacaEval, and GSM8K show 35‑43% speedups with less than 2% accuracy loss, facilitating practical on‑device LLM deployment without specialized infrastructure.
arXiv:2608. 04048v1 Announce Type: cross Abstract: Serving large language models (LLMs) under diverse deployment constraints requires flexible trade-offs between accuracy, memory footprint, and throughput.
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.
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:2606. 10531v1 Announce Type: cross Abstract: Quantization-aware training (QAT) is essential for extremely low-bit large language models (LLMs).
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.