The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
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.
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: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,...
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.
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: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.