Large language models (LLMs) have demonstrated strong capabilities in handling long-context tasks, but processing such long contexts remains challenging due to the substantial memory requirements and inference latency. In this work, we discover that certain attention heads exhibit sequential consistency in their attention patterns, which can be persistently identified using a coefficient-of-variation-based algorithm. Inspired by this observation, we propose CateKV, a hybrid KV cache method that retains only critical token information for consistent heads, thereby reducing KV cache size and computational overhead, while preserving the majority of KV pairs in adaptive heads to ensure high accuracy. We show the unique characteristics of our algorithm and its extension with existing acceleration methods. Comprehensive evaluations on long-context benchmarks show that, while maintaining accuracy comparable to full attention, CateKV reduces memory usage by up to $2.72\times$ and accelerates decoding by $2.18\times$ in single-sample inputs, and boosts throughput by $3.96\times$ in batch scenarios.

Silicon carbide (SiC) metal oxide semiconductor field-effect transistor (MOSFET) is increasingly being used in EVs inverters because of its high switching frequency, switching speed and operating temperature characteristics. However, these characteristics can lead to a rapid increase in temperature, resulting in thermal failure of the power inverter. Therefore, predicting the SiC MOSFET junction temperature is vital for effective thermal management. First, this article establishes the SiC MOSFET electrical model to calculate the loss and obtains the loss parameters through double-pulse experiments. Next, a novel coupled thermal network model is introduced, accompanied by the development of a 3D finite element model to derive the SiC MOSFET thermal parameters. Finally, a$S$iC MOSFET power module electro-thermal coupled model is developed to predict its junction temperature and the experimental outcomes demonstrated the reliability of this method.

Graph neural networks (GNNs) suffer from low GPU utilization due to frequent memory accesses. Existing concurrent training mechanisms cannot be directly adapted to GNNs because they fail to consider the impact of input irregularity. This requires pre-profiling the memory footprint of concurrent tasks based on input dimensions to ensure successful co-location on GPU. Moreover, massive training tasks generated from scenarios such as hyper-parameter tuning require flexible scheduling strategies. To address these problems, we propose CoGNN that enables efficient management of GNN training tasks on GPUs. Specifically, the CoGNN organizes the tasks in a queue and estimates the memory consumption of each task based on cost functions at operator basis. In addition, the CoGNN implements scheduling policies to generate task groups, which are iteratively submitted for execution. The experiment results show that the CoGNN can achieve shorter completion and queuing time for training tasks from diverse GNN models.

We present FleetRec, a high-performance and scalable recommendation inference system within tight latency constraints. FleetRec takes advantage of heterogeneous hardware including GPUs and the latest FPGAs equipped with high-bandwidth memory. By disaggregating computation and memory to different types of hardware and bridging their connections by high-speed network, FleetRec gains the best of both worlds, and can naturally scale out by adding nodes to the cluster. Experiments on three production models up to 114 GB show that FleetRec outperforms optimized CPU baseline by more than one order of magnitude in terms of throughput while achieving significantly lower latency.

GraphScope is a system and a set of language extensions that enable a new programming interface for large-scale distributed graph computing. It generalizes previous graph processing frameworks (e.g. , Pregel, GraphX) and distributed graph databases ( e.g ., Janus-Graph, Neptune) in two important ways: by exposing a unified programming interface to a wide variety of graph computations such as graph traversal, pattern matching, iterative algorithms and graph neural networks within a high-level programming language; and by supporting the seamless integration of a highly optimized graph engine in a general purpose data-parallel computing system. A GraphScope program is a sequential program composed of declarative data-parallel operators, and can be written using standard Python development tools. The system automatically handles the parallelization and distributed execution of programs on a cluster of machines. It outperforms current state-of-the-art systems by enabling a separate optimization (or family of optimizations) for each graph operation in one carefully designed coherent framework. We describe the design and implementation of GraphScope and evaluate system performance using several real-world applications.