Recent advances in agentic large language models (LLMs) have substantially improved Text-to-SQL, enabling users without database expertise to query databases intuitively. However, deploying agentic LLM-based Text-to-SQL systems in production remains challenging due to multi-stage dependencies, strict latency requirements, and deployment complexity across heterogeneous GPUs in enterprise clusters. Existing LLM serving frameworks are designed mainly for independent inference tasks, leading to suboptimal performance and frequent service-level objective (SLO) violations for Text-to-SQL workloads. In this paper, we introduce \sys, a framework for scheduling and executing agentic multi-stage LLM-based Text-to-SQL workflows on heterogeneous GPU clusters serving multi-tenant requests. \sys adopts a hierarchical scheduler that combines global workload-balanced task dispatching with an adaptive local priority queue, guided by a systematic analysis of agentic Text-to-SQL workflows. We also propose a lightweight simulation-based method to tune key scheduling hyperparameters, improving robustness and adaptability. Evaluations on realistic Text-to-SQL benchmarks show that \sys significantly outperforms state-of-the-art LLM serving frameworks. Across all traces, \sys reduces P95 tail latency by $1.42{\sim}1.56\times$ and increases throughput by $1.49{\sim}1.81\times$, demonstrating consistent gains under diverse workloads.

Disaggregating the prefill and decoding phases represents an effective new paradigm for generative inference of large language models (LLM). This approach offers some significant system advantages, such as eliminating prefill-decoding interference and optimizing resource allocation. However, it is still an challenging open problem about how to deploy the disaggregated inference paradigm across a group of heterogeneous GPUs, which can be an economic alternative of the deployment over the homogeneous high performance GPUs. Towards this end, we introduce HexGen-2, a distributed system for high throughput and cost-efficient LLM serving on heterogeneous GPUs following the disaggragated paradigm. Built on top of HexGen, the core component of HexGen-2 is a sophisticated scheduling algorithm that formalizes the allocation of disaggregated LLM inference computations and communications over heterogeneous GPUs and network connections as a constraint optimization problem. We leverage the graph partitioning and max-flow algorithm to co-optimize resource allocation, parallel strategies for distinct inference phases, and the efficiency of inter-phase key-value (KV) cache communications. We conduct extensive experiments to evaluate HexGen-2, i.e., on OPT (30B) and Llama-2 (70B) models in various real-world settings, the results reveal that HexGen-2 delivers up to a 2.0$\times$ and on average a 1.3$\times$ improvement in serving throughput, reduces the average inference latency by 1.5$\times$ compared with state-of-the-art systems given the same price budget, and achieves comparable inference performance with a 30% lower price budget.

Recent advancements in Large Language Models (LLMs) have led to increasingly diverse requests, accompanied with varying resource (compute and memory) demands to serve them. However, this in turn degrades the cost-efficiency of LLM serving as common practices primarily rely on homogeneous GPU resources. In response to this problem, this work conducts a thorough study about serving LLMs over heterogeneous GPU resources on cloud platforms. The rationale is that different GPU types exhibit distinct compute and memory characteristics, aligning well with the divergent resource demands of diverse requests. Particularly, through comprehensive benchmarking, we discover that the cost-efficiency of LLM serving can be substantially optimized by meticulously determining GPU composition, deployment configurations, and workload assignments. Subsequently, we design a scheduling algorithm via mixed-integer linear programming, aiming at deducing the most cost-efficient serving plan under the constraints of price budget and real-time GPU availability. Remarkably, our approach effectively outperforms homogeneous and heterogeneous baselines under a wide array of scenarios, covering diverse workload traces, varying GPU availablilities, and multi-model serving. This casts new light on more accessible and efficient LLM serving over heterogeneous cloud resources.

The scaling law for large language models (LLMs) depicts that the path towards machine intelligence necessitates training at large scale. Thus, companies continuously build large-scale GPU clusters, and launch training jobs that span over thousands of computing nodes. However, LLM pre-training presents unique challenges due to its complex communication patterns, where GPUs exchange data in sparse yet high-volume bursts within specific groups. Inefficient resource scheduling exacerbates bandwidth contention, leading to suboptimal training performance. This paper presents Arnold, a scheduling system summarizing our experience to effectively align LLM communication patterns to data center topology at scale. In-depth characteristic study is performed to identify the impact of physical network topology to LLM pre-training jobs. Based on the insights, we develop a scheduling algorithm to effectively align communication patterns to physical network topology in data centers. Through simulation experiments, we show the effectiveness of our algorithm in reducing the maximum spread of communication groups by up to $1.67$x. In production training, our scheduling system improves the end-to-end performance by $10.6\%$ when training with more than $9600$ Hopper GPUs, a significant improvement for our training pipeline.

Serving generative inference of the large language model is a crucial component of contemporary AI applications. In this paper, our focus lies in deploying such services in a heterogeneous and cross-datacenter setting to mitigate the substantial inference costs typically associated with a single centralized datacenter. Towards this end, we propose HexGen, a flexible distributed inference engine that uniquely supports the asymmetric partition of generative inference computations over both tensor model parallelism and pipeline parallelism, which allows for effective deployment across diverse GPUs interconnected by a fully heterogeneous network. We further propose a sophisticated scheduling algorithm grounded in constrained optimization that can adaptively assign asymmetric inference computation across the GPUs to fulfill inference requests while maintaining acceptable latency levels. We conduct an extensive empirical study to evaluate the efficiency of HexGen by serving the state-of-the-art Llama-2 (70B) model. The experimental results suggest that HexGen can choose to achieve up to $2.3\times$ lower latency deadlines or tolerate up to $4\times$ more traffic request rates compared with the homogeneous baseline given the same budget.

Graph neural networks (GNNs) have emerged as the state of the art for a variety of graph-related tasks and have been widely commercialized in real-world scenarios. Behind its revolutionary representation capability, the huge training costs also expose GNNs to the risks of potential model piracy attacks which threaten the intellectual property (IP) of GNNs. In this work, we design a novel and effective ownership verification framework for GNNs called GNNFingers to safeguard the IP of GNNs. The key design of the proposed framework is two-fold: graph fingerprint construction and robust verification module. With GNNFingers, a GNN model owner can verify if a deployed model is stolen from the source GNN simply by querying with graph inputs. Besides, GNNFingers could be applied to various GNN models and graph-related tasks. We extensively evaluate the proposed framework on various GNNs designed for multiple graph-related tasks including graph classification, graph matching, node classification, and link prediction. Our results show that GNNFingers can robustly distinguish post-processed surrogate GNNs from irrelevant GNNs, e.g., GNNFingers achieves 100% true positives and 100% true negatives on the test of 200 suspect GNNs of both graph classification and node classification tasks.

Transformer models have emerged as the leading approach for achieving state-of-the-art performance across various application domains, serving as the foundation for advanced large-scale deep learning (DL) models. However, efficiently training these models across multiple GPUs remains a complex challenge due to the abundance of parallelism options. Existing DL systems either require manual efforts to design distributed training plans or limit parallelism combinations to a constrained search space. In this paper, we present Galvatron-BMW, a novel system framework that integrates multiple prevalent parallelism dimensions and automatically identifies the most efficient hybrid parallelism strategy. To effectively navigate this vast search space, we employ a decision tree approach for decomposition and pruning based on intuitive insights. We further utilize a dynamic programming search algorithm to derive the optimal plan. Moreover, to improve resource utilization and enhance system efficiency, we propose a bi-objective optimization workflow that focuses on workload balance. Our evaluations on different Transformer models demonstrate the capabilities of Galvatron-BMW in automating distributed training under varying GPU memory constraints. Across all tested scenarios, Galvatron-BMW consistently achieves superior system throughput, surpassing previous approaches that rely on limited parallelism strategies.

Large-scale deep learning models contribute to significant performance improvements on varieties of downstream tasks. Current data and model parallelism approaches utilize model replication and partition techniques to support the distributed training of ultra-large models. However, directly deploying these systems often leads to sub-optimal training efficiency due to the complex model architectures and the strict device memory constraints. In this paper, we propose Optimal Sharded Data Parallel (OSDP), an automated parallel training system that combines the advantages from both data and model parallelism. Given the model description and the device information, OSDP makes trade-offs between the memory consumption and the hardware utilization, thus automatically generates the distributed computation graph and maximizes the overall system throughput. In addition, OSDP introduces operator splitting to further alleviate peak memory footprints during training with negligible overheads, which enables the trainability of larger models as well as the higher throughput. Extensive experimental results of OSDP on multiple different kinds of large-scale models demonstrate that the proposed strategy outperforms the state-of-the-art in multiple regards.

Transformer models have achieved state-of-the-art performance on various domains of applications and gradually becomes the foundations of the advanced large deep learning (DL) models. However, how to train these models over multiple GPUs efficiently is still challenging due to a large number of parallelism choices. Existing DL systems either rely on manual efforts to make distributed training plans or apply parallelism combinations within a very limited search space. In this approach, we propose Galvatron, a new system framework that incorporates multiple popular parallelism dimensions and automatically finds the most efficient hybrid parallelism strategy. To better explore such a rarely huge search space, we 1) involve a decision tree to make decomposition and pruning based on some reasonable intuitions, and then 2) design a dynamic programming search algorithm to generate the optimal plan. Evaluations on four representative Transformer workloads show that Galvatron could perform automatically distributed training with different GPU memory budgets. Among all evaluated scenarios, Galvatron always achieves superior system throughput compared to previous work with limited parallelism.