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.
Recent foundation models are moving toward native multimodal Vision-Language Models (VLMs), making VLMs a central form of next-generation foundation models. However, their large language backbones mak...
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: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:2502. 00527v2 Announce Type: replace Abstract: The KV cache in large language models is a dominant factor in memory usage, limiting their broader applicability.
arXiv:2608.30384v1 Announce Type: new Abstract: By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1--4 bits per dimension,...
The paper introduces TORQUE, a framework that enhances quantization by jointly optimizing which coordinates to keep at high precision before and after applying uniform random rotations, all within a fixed bit budget. By preserving large input coordinates before rotation and the largest-magnitude coordinates after rotation, TORQUE reduces quantization error and allows efficient use of offline-optimized codebooks. The authors provide an error upper bound, prove that top‑k pre‑rotation retention is optimal for each k, and demonstrate improved accuracy‑storage tradeoffs in Gaussian models and practical tasks such as nearest‑neighbor retrieval, KV‑cache compression, and activation compression.
arXiv:2605. 26092v4 Announce Type: replace-cross Abstract: The deployment of Large Language Models (LLMs) and Vision Transformers (ViTs) on edge devices is significantly constrained by memory limitations and the critical timing bottlenecks introduced by dense Multiply-Accumulate (MAC) arrays.
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: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:2505. 18231v3 Announce Type: replace-cross Abstract: Large Language Model (LLM) inference is typically memory-intensive, especially when processing large batch sizes and long sequences, due to the large size of key-value (KV) cache.
arXiv:2601. 21626v2 Announce Type: replace-cross Abstract: Post Training Quantization (PTQ), a mainstream model compression technique, often leads to the paradoxical 'low error, high loss' phenomenon because it focuses solely on minimizing quantization error.
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.