Haiyang Shi

The AIBrix Team, Jiaxin Shan, Varun Gupta et al.

We introduce AIBrix, a cloud-native, open-source framework designed to optimize and simplify large-scale LLM deployment in cloud environments. Unlike traditional cloud-native stacks, AIBrix follows a co-design philosophy, ensuring every layer of the infrastructure is purpose-built for seamless integration with inference engines like vLLM. AIBrix introduces several key innovations to reduce inference costs and enhance performance including high-density LoRA management for dynamic adapter scheduling, LLM-specific autoscalers, and prefix-aware, load-aware routing. To further improve efficiency, AIBrix incorporates a distributed KV cache, boosting token reuse across nodes, leading to a 50% increase in throughput and a 70% reduction in inference latency. AIBrix also supports unified AI runtime which streamlines model management while maintaining vendor-agnostic engine compatibility. For large-scale multi-node inference, AIBrix employs hybrid orchestration -- leveraging Kubernetes for coarse-grained scheduling and Ray for fine-grained execution -- to balance efficiency and flexibility. Additionally, an SLO-driven GPU optimizer dynamically adjusts resource allocations, optimizing heterogeneous serving to maximize cost efficiency while maintaining service guarantees. Finally, AIBrix enhances system reliability with AI accelerator diagnostic tools, enabling automated failure detection and mock-up testing to improve fault resilience. AIBrix is available at https://github.com/vllm-project/aibrix.

Haiyang Shi

The application of process-based and data-driven hydrological models is crucial in modern hydrological research, especially for predicting key water cycle variables such as runoff, evapotranspiration (ET), and soil moisture. These models provide a scientific basis for water resource management, flood forecasting, and ecological protection. Process-based models simulate the physical mechanisms of watershed hydrological processes, while data-driven models leverage large datasets and advanced machine learning algorithms. This paper reviewed and compared methods for assessing and enhancing the extrapolability of both model types, discussing their prospects and limitations. Key strategies include the use of leave-one-out cross-validation and similarity-based methods to evaluate model performance in ungauged regions. Deep learning, transfer learning, and domain adaptation techniques are also promising in their potential to improve model predictions in data-sparse and extreme conditions. Interdisciplinary collaboration and continuous algorithmic advancements are also important to strengthen the global applicability and reliability of hydrological models.

Haiyang Shi

Due to the heterogeneity of the global distribution of ecological and hydrological ground-truth observations, machine learning models can have limited adaptability when applied to unknown locations, which is referred to as weak extrapolability. Domain adaptation techniques have been widely used in machine learning domains such as image classification, which can improve the model generalization ability by adjusting the difference or inconsistency of the domain distribution between the training and test sets. However, this approach has rarely been used explicitly in machine learning models in ecology and hydrology at the global scale, although these models have often been questioned due to geographic extrapolability issues. This paper briefly describes the shortcomings of current machine learning models of ecology and hydrology in terms of the global representativeness of the distribution of observations and the resulting limitations of the lack of extrapolability and suggests that future related modelling efforts should consider the use of domain adaptation techniques to improve extrapolability.

Kan Zhu, Haiyang Shi, Le Xu et al.

Advances in Large Language Models (LLMs) have led to a surge of LLM-powered applications. These applications have diverse token-generation latency requirements. As a result, simply classifying workloads as latency-sensitive (LS) or best-effort (BE) overlooks the nuances within the latency-sensitive category and results in suboptimal user experiences and scheduling opportunities. However, efficiently serving requests with multiple SLO requirements poses significant challenges. First, all requests within a batch generate new tokens simultaneously, which can misalign them with their distinct SLO requirements. Moreover, while existing systems focus on auto-scaling for handling various overall request rates, the diversity of SLOs necessitates fine-grained auto-scaling among these SLO tiers. Finally, unlike LS/BE scenarios, where BE requests can be aborted at any time to ensure the SLO attainment of LS requests, those with different latency-sensitive SLOs cannot tolerate prolonged delays, and tail latency must be controlled. To tackle these challenges, we propose PolyServe, a novel multi-SLO scheduling policy at scale that maintains high SLO attainment while maximizing throughput. PolyServe first groups requests into multiple bins based on their per-token latency requirement, then schedules each bin to a subset of the server fleet. PolyServe routes requests to the highest-load but still SLO-attainable server to create a load gradient that facilitates auto-scaling. To increase utilization, PolyServe permits looser-SLO requests to share tighter-SLO instances when their own servers are saturated. PolyServe uses profiling data to guide scheduling decisions and manage tail latency through request-wait-time-aware scheduling, dynamic chunking, and continuous chunked prefill prediction. PolyServe achieves 1.23x goodput gain compared to existing policies, achieving up to 92.5% of optimal goodput.

Haiyang Shi

Machine learning-based hydrological prediction models, despite their high accuracy, face limitations in extrapolation capabilities when applied globally due to uneven data distribution. This study integrates Domain-Adversarial Neural Networks (DANN) to improve the geographical adaptability of evapotranspiration (ET) models. By employing DANN, we aim to mitigate distributional discrepancies between different sites, significantly enhancing the model's extrapolation capabilities. Our results show that DANN improves ET prediction accuracy with an average increase in the Kling-Gupta Efficiency (KGE) of 0.2 to 0.3 compared to the traditional Leave-One-Out (LOO) method. DANN is particularly effective for isolated sites and transition zones between biomes, reducing data distribution discrepancies and avoiding low-accuracy predictions. By leveraging information from data-rich areas, DANN enhances the reliability of global-scale ET products, especially in ungauged regions. This study highlights the potential of domain adaptation techniques to improve the extrapolation and generalization capabilities of machine learning models in hydrological studies.