Related papers: UCCL-Zip: Lossless Compression Supercharged GPU Co…

Error-bounded lossy compression is a critical technique for significantly reducing scientific data volumes. Compared to CPU-based compressors, GPU-based compressors exhibit substantially higher throughputs, fitting better for today's HPC…

Serving Large Language Models (LLMs) in production faces significant challenges from highly variable request patterns and severe resource fragmentation in serverless clusters. Current systems rely on static pipeline configurations that…

Training large language models (LLMs) is fundamentally constrained by limited device memory and costly inter-device communication. Although pipeline parallelism alleviates memory pressure by partitioning models across devices, it incurs…

In deepfake detection, the varying degrees of compression employed by social media platforms pose significant challenges for model generalization and reliability. Although existing methods have progressed from single-modal to multimodal…

In this paper, we propose UniLIP, a unified framework that adapts CLIP for multimodal understanding, generation and editing. Although CLIP excels at understanding, it lacks reconstruction abilities required to be a unified visual encoder.…

We propose Deep Lossless Image Coding (DLIC), a full resolution learned lossless image compression algorithm. Our algorithm is based on a neural network combined with an entropy encoder. The neural network performs a density estimation on…

Learning-based point cloud compression methods have made significant progress in terms of performance. However, these methods still encounter challenges including high complexity, limited compression modes, and a lack of support for…

Large Language Models (LLMs) achieve strong performance across tasks, but face storage and compute challenges on edge devices. We propose EntroLLM, a compression framework combining mixed quantization and entropy coding to reduce storage…

Transformer-based Large Language Models (LLMs) have made a significant impact on various domains. However, LLMs' efficiency suffers from both heavy computation and memory overheads. Compression techniques like sparsification and…

Modern graphics processors provide exceptional computa- tional power, but only for certain computational models. While they have revolutionized computation in many fields, compression has been largely unnaffected. This paper aims to explain…

As they become more capable, large language models (LLMs) have continued to rapidly increase in size. This has exacerbated the difficulty in running state of the art LLMs on small, edge devices. Standard techniques advocate solving this…

The rapid growth in the size of large language models has necessitated the partitioning of computational workloads across accelerators such as GPUs, TPUs, and NPUs. However, these parallelization strategies incur substantial data…

Large language models are increasingly capable of handling long-context inputs, but the memory overhead of key-value (KV) cache remains a major bottleneck for general-purpose deployment. While various compression strategies have been…

We present Nacrith, a lossless compression system that combines a 135M-parameter transformer language model (SmolLM2-135M) with an ensemble of lightweight online predictors and a 32-bit arithmetic coder, achieving the best compression…

An important ingredient of the future 5G systems will be Ultra-Reliable Low-Latency Communication (URLLC). A way to offer URLLC without intervention in the baseband/PHY layer design is to use \emph{interface diversity} and integrate…

To alleviate hardware scarcity in training large deep neural networks (DNNs), particularly large language models (LLMs), we present FusionLLM, a decentralized training system designed and implemented for training DNNs using geo-distributed…

UCX is a communication framework that enables low-latency, high-bandwidth communication in HPC systems. With its unified API, UCX facilitates efficient data transfers across multi-node CPU-GPU clusters. UCX is widely used as the transport…

Graph contrastive learning (GCL) has recently emerged as an effective learning paradigm to alleviate the reliance on labelling information for graph representation learning. The core of GCL is to maximise the mutual information between the…

In the realm of Large Language Model (LLM) inference, the inherent structure of transformer models coupled with the multi-GPU tensor parallelism strategy leads to a sequential execution of computation and communication. This results in…

Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual learning (SCL) scenarios. Consequently, they are not scalable…