Related papers: The Geometry of LLM Quantization: GPTQ as Babai's …

Although recent quantized Large Language Models (LLMs), such as BitNet, have paved the way for significant reduction in memory usage during deployment with binary or ternary weights, training these models still demands substantial memory…

Large language models (LLMs) have shown immense potential across various domains, but their high memory requirements and inference costs remain critical challenges for deployment. Post-training quantization (PTQ) has emerged as a promising…

We study the Maximum Weight Matching (MWM) problem for general graphs through the max-product Belief Propagation (BP) and related Linear Programming (LP). The BP approach provides distributed heuristics for finding the Maximum A Posteriori…

Large Language Models (LLMs) from the GPT family have become extremely popular, leading to a race towards reducing their inference costs to allow for efficient local computation. Yet, the vast majority of existing work focuses on…

Quantizing large language models has become a standard way to reduce their memory and computational costs. Typically, existing methods focus on breaking down the problem into individual layer-wise sub-problems, and minimizing per-layer…

There has been significant interest in "extreme" compression of large language models (LLMs), i.e., to 1-2 bits per parameter, which allows such models to be executed efficiently on resource-constrained devices. Existing work focused on…

Mixture-of-Experts Large Language Models (MoE-LLMs) achieve strong performance but incur substantial memory overhead due to massive expert parameters. Mixed-precision quantization mitigates this cost by allocating expert-wise bit-widths…

We study the generalized multidimensional bin packing problem (GVBP) that generalizes both geometric packing and vector packing. Here, we are given $n$ rectangular items where the $i^{\textrm{th}}$ item has width $w(i)$, height $h(i)$, and…

Post-training quantization (PTQ) is a widely used method to compress large language models (LLMs) without fine-tuning. It typically sets quantization hyperparameters (e.g., scaling factors) based on current-layer activations. Although this…

In the field of deep learning, traditional attention mechanisms face significant challenges related to high computational complexity and large memory consumption when processing long sequence data. To address these limitations, we propose…

Model compression has gained a lot of attention due to its ability to reduce hardware resource requirements significantly while maintaining accuracy of DNNs. Model compression is especially useful for memory-intensive recurrent neural…

Recent advances in large language model (LLM) pretraining have led to high-quality LLMs with impressive abilities. By compressing such LLMs via quantization to 3-4 bits per parameter, they can fit into memory-limited devices such as laptops…

Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process. This paper addresses these challenges by focusing on…

Large-scale pre-trained Vision-Language Models (VLMs) have gained prominence in various visual and multimodal tasks, yet the deployment of VLMs on downstream application platforms remains challenging due to their prohibitive requirements of…

Diffusion large language models (dLLMs), which offer bidirectional context and flexible masked-denoising generation, are emerging as a compelling alternative to autoregressive (AR) LLMs. However, like AR LLMs, their model sizes continue to…

Existing post-training quantization methods for large language models (LLMs) offer remarkable success. However, the increasingly marginal performance gains suggest that existing quantization strategies are insufficient to support the…

Large Language Models (LLMs) typically rely on a large number of parameters for token embedding, leading to substantial storage requirements and memory footprints. In particular, LLMs deployed on edge devices are memory-bound, and reducing…

Trajectory prediction is a fundamental task for autonomous systems, requiring complex reasoning about multi-agent interactions and intents. Large language models (LLMs) have recently been adopted for this task, as they provide strong…

Large Language Models (LLMs) have revolutionized the field of Natural Language Processing thanks to their ability to reuse knowledge acquired on massive text corpora on a wide variety of downstream tasks, with minimal (if any) tuning steps.…

Topological quantum error correction is a milestone in the scaling roadmap of quantum computers, which targets circuits with trillions of gates that would allow running quantum algorithms for real-world problems. The square-lattice surface…