arXiv:2507. 23035v4 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated impressive capabilities across a wide range of applications, but demand substantial memory and compute resources during inference.
arXiv:2606. 15652v1 Announce Type: new Abstract: 4-bit quantization significantly reduces the memory footprint and accelerates the inference of large language models (LLMs).
arXiv:2606. 07116v1 Announce Type: cross Abstract: Low-bit quantization has been widely adopted to accelerate the inference of large language models (LLMs) by significantly reducing computational cost and memory usage.
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:2601. 07475v2 Announce Type: replace-cross Abstract: The emergence of fine-grained numerical formats like NVFP4 presents new opportunities for efficient Large Language Model (LLM) inference.
arXiv:2606. 04620v1 Announce Type: cross Abstract: LLMs have become the state-of-the-art algorithms for solving NLP tasks.
arXiv:2604. 10496v2 Announce Type: replace Abstract: Outliers have emerged as a fundamental bottleneck in preserving accuracy for low-precision large models, particularly within Mixture-of-Experts (MoE) architectures that are increasingly central to large-scale language modeling.
arXiv:2608. 15602v1 Announce Type: cross Abstract: While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of specialized hardware kernels, thus failing to unleash the full acceleration potential due to persistent reliance on expensive floating-point arithmetic or runtime dequantization overheads.
SPHQuant introduces a rotation‑free spherical weight‑only quantization framework for Vision‑Language Models, decomposing 8‑dimensional weight vectors into sign, radius, and a positive unit direction. By isolating outlier magnitudes in the radius and allocating extra precision there, it mitigates accuracy loss at extreme low bit‑widths. The method also employs a compact positive‑direction codebook with angular fine‑tuning and a hardware‑friendly GEMV kernel, achieving state‑of‑the‑art performance while boosting decode throughput by 30.3% on RTX A6000 compared to QTIP.
ConQuR introduces a lightweight post‑training rotation calibration for large language model activation quantization. By learning orthogonal rotations that align normalized activations with the corners of an inscribed hypercube, the method distributes activation energy evenly and can be updated online without storing activations. Experiments on Llama‑2 and Llama‑3 models (3B–70B) show competitive or improved perplexity and reasoning performance while avoiding costly training or large offline storage.
arXiv:2506. 04985v2 Announce Type: replace Abstract: Large language models (LLMs) require substantial compute, and thus energy, at inference time.
HBQ: Hierarchical Scaling Block Quantization with Hardware‑Efficiency‑Aware Design for Accurate LLM Inference proposes a new block‑quantization scheme that uses large blocks and low‑overhead significand scaling to balance hardware efficiency and accuracy. The authors demonstrate that larger blocks improve efficiency by amortizing dequantization and accumulation costs, while their SIG scaling compensates for the resulting accuracy loss. Experiments on a 28 nm ASIC accelerator show that HBQ achieves up to 4.6× higher area/energy efficiency than state‑of‑the‑art weight‑only quantization, with 1.5–3.0× speedup and 1.6–3.3× system energy reduction over existing BQ methods.
arXiv:2606. 26587v1 Announce Type: cross Abstract: Low-bit floating-point formats and semi-structured sparsity are increasingly supported by modern accelerators, yet combining them for LLM activation compression remains challenging: activations contain input-dependent outliers that dominate block scales in FP4 quantization, and directly applying N:M sparsity masks discards moderate values, coupling sparsification loss with quantization error.