Related papers: QSVD: Efficient Low-rank Approximation for Unified…
Autoregressive decoding in large language models (LLMs) requires caching a growing list of past key-value (KV) pairs, making long-context inference a memory-bound problem. While recent methods have explored quantizing the cache, evicting…
Vector quantization(VQ) is a hardware-friendly DNN compression method that can reduce the storage cost and weight-loading datawidth of hardware accelerators. However, conventional VQ techniques lead to significant accuracy loss because the…
Vision-Language Models (VLMs) excel in diverse visual tasks but face challenges in document understanding, which requires fine-grained text processing. While typical visual tasks perform well with low-resolution inputs, reading-intensive…
Large Language Models (LLMs) have revolutionized a wide range of domains such as natural language processing, computer vision, and multi-modal tasks due to their ability to comprehend context and perform logical reasoning. However, the…
The rapid growth of visual data under stringent storage and bandwidth constraints makes extremely low-bitrate image compression increasingly important. While Vector Quantization (VQ) offers strong structural fidelity, existing methods lack…
Visual Mamba networks (ViMs) extend the selective state space model (Mamba) to various vision tasks and demonstrate significant potential. As a promising compression technique, vector quantization (VQ) decomposes network weights into…
There are several factorizations of multi-dimensional tensors into lower-dimensional components, known as `tensor networks'. We consider the popular `tensor-train' (TT) format and ask: How efficiently can we compute a low-rank approximation…
Approaches for compressing large-language models using low-rank decomposition have made strides, particularly with the introduction of activation and loss-aware SVD, which improves the trade-off between decomposition rank and downstream…
Existing key-value (KV) cache compression methods typically rely on heuristics, such as uniform cache allocation across layers or static eviction policies, however, they ignore the critical interplays among layer-specific feature patterns…
In this paper we present a new approach of incorporating kernels into dictionary learning. The kernel K-SVD algorithm (KKSVD), which has been introduced recently, shows an improvement in classification performance, with relation to its…
Scaling model size significantly challenges the deployment and inference of Large Language Models (LLMs). Due to the redundancy in LLM weights, recent research has focused on pushing weight-only quantization to extremely low-bit (even down…
Large Language Models (LLMs) have achieved impressive accomplishments in recent years. However, the increasing memory consumption of KV cache has possessed a significant challenge to the inference system. Eviction methods have revealed the…
This paper presents a portable, GPU-accelerated implementation of a QR-based singular value computation algorithm in Julia. The singular value ecomposition (SVD) is a fundamental numerical tool in scientific computing and machine learning,…
Recent low-rank training methods, such as GaLore, have significantly reduced the memory required to optimize large language models (LLMs). However, these methods often suffer from time-consuming low-rank projection estimations. In…
Recently, large language models (LLMs) have shown surprising performance in task-specific workloads as well as general tasks with the given prompts. However, to achieve unprecedented performance, recent LLMs use billions to trillions of…
Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in long-context inference. Prior KV cache…
Withtherapid advancement of large language models (LLMs), the context length for inference has been continuously increasing, leading to an exponential growth in the demand for Key-Value (KV) caching. This has resulted in a significant…
KV cache eviction has emerged as an effective solution to alleviate resource constraints faced by LLMs in long-context scenarios. However, existing token-level eviction methods often overlook two critical aspects: (1) their irreversible…
We introduce MUSE-VL, a Unified Vision-Language Model through Semantic discrete Encoding for multimodal understanding and generation. Recently, the research community has begun exploring unified models for visual generation and…
Singular value decomposition (SVD) and matrix inversion are ubiquitous in scientific computing. Both tasks are computationally demanding for large scale matrices. Existing algorithms can approximatively solve these problems with a given…