HybridFlow: A Flexible and Efficient RLHF Framework

• URL: http://arxiv.org/abs/2409.19256v2
• Date: Wed, 2 Oct 2024 04:01:47 GMT
• Title: HybridFlow: A Flexible and Efficient RLHF Framework
• Authors: Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, Chuan Wu,
• Abstract summary: Reinforcement Learning from Human Feedback is widely used in Large Language Model (LLM) alignment. Traditional RL can be modeled as a dataflow, where each node represents computation of a neural network (NN) We propose HybridFlow, which combines single-controller and multi-controller paradigms in a hybrid manner to enable flexible representation and efficient execution of the RLHF dataflow.
• Score: 13.80577212781375
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning from Human Feedback (RLHF) is widely used in Large Language Model (LLM) alignment. Traditional RL can be modeled as a dataflow, where each node represents computation of a neural network (NN) and each edge denotes data dependencies between the NNs. RLHF complicates the dataflow by expanding each node into a distributed LLM training or generation program, and each edge into a many-to-many multicast. Traditional RL frameworks execute the dataflow using a single controller to instruct both intra-node computation and inter-node communication, which can be inefficient in RLHF due to large control dispatch overhead for distributed intra-node computation. Existing RLHF systems adopt a multi-controller paradigm, which can be inflexible due to nesting distributed computation and data communication. We propose HybridFlow, which combines single-controller and multi-controller paradigms in a hybrid manner to enable flexible representation and efficient execution of the RLHF dataflow. We carefully design a set of hierarchical APIs that decouple and encapsulate computation and data dependencies in the complex RLHF dataflow, allowing efficient operation orchestration to implement RLHF algorithms and flexible mapping of the computation onto various devices. We further design a 3D-HybridEngine for efficient actor model resharding between training and generation phases, with zero memory redundancy and significantly reduced communication overhead. Our experimental results demonstrate 1.53$\times$~20.57$\times$ throughput improvement when running various RLHF algorithms using HybridFlow, as compared with state-of-the-art baselines. HybridFlow source code will be available at https://github.com/volcengine/verl.

Related papers

• FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression [55.992528247880685]
  Decentralized training faces significant challenges regarding system design and efficiency. We present FusionLLM, a decentralized training system designed and implemented for training large deep neural networks (DNNs) We show that our system and method can achieve 1.45 - 9.39x speedup compared to baseline methods while ensuring convergence.
  arXiv  Detail & Related papers  (2024-10-16T16:13:19Z)
• RLHFuse: Efficient RLHF Training for Large Language Models with Inter- and Intra-Stage Fusion [10.165579735221092]
  Existing RLHF systems suffer from low GPU utilization in production deployments. RLHFuse breaks the traditional view of RLHF workflow as a composition of individual tasks. RLHFuse increases the training throughput by up to 3.7x, compared to existing state-of-the-art systems.
  arXiv  Detail & Related papers  (2024-09-20T05:15:38Z)
• RLHF Workflow: From Reward Modeling to Online RLHF [79.83927049253924]
  We present the workflow of Online Iterative Reinforcement Learning from Human Feedback (RLHF) in this technical report. RLHF is widely reported to outperform its offline counterpart by a large margin in the recent large language model (LLM) literature. We show that supervised fine-tuning (SFT) and iterative RLHF can obtain state-of-the-art performance with fully open-source datasets.
  arXiv  Detail & Related papers  (2024-05-13T15:50:39Z)
• Efficient Parallel Reinforcement Learning Framework using the Reactor Model [2.190190313041532]
  Reinforcement Learning (RL) frameworks are essential for mapping RL workloads to multiple computational resources. Existing frameworks, such as Ray, are not managing this orchestration efficiently. We have proposed a solution implementing the reactor model, which enforces a set of actors to have a fixed communication pattern.
  arXiv  Detail & Related papers  (2023-12-07T21:19:57Z)
• In Situ Framework for Coupling Simulation and Machine Learning with Application to CFD [51.04126395480625]
  Recent years have seen many successful applications of machine learning (ML) to facilitate fluid dynamic computations. As simulations grow, generating new training datasets for traditional offline learning creates I/O and storage bottlenecks. This work offers a solution by simplifying this coupling and enabling in situ training and inference on heterogeneous clusters.
  arXiv  Detail & Related papers  (2023-06-22T14:07:54Z)
• Auto-FedRL: Federated Hyperparameter Optimization for Multi-institutional Medical Image Segmentation [48.821062916381685]
  Federated learning (FL) is a distributed machine learning technique that enables collaborative model training while avoiding explicit data sharing. In this work, we propose an efficient reinforcement learning(RL)-based federated hyperparameter optimization algorithm, termed Auto-FedRL. The effectiveness of the proposed method is validated on a heterogeneous data split of the CIFAR-10 dataset and two real-world medical image segmentation datasets.
  arXiv  Detail & Related papers  (2022-03-12T04:11:42Z)
• OneFlow: Redesign the Distributed Deep Learning Framework from Scratch [17.798586916628174]
  OneFlow is a novel distributed training framework based on an SBP (split, broadcast and partial-value) abstraction and the actor model. SBP enables much easier programming of data parallelism and model parallelism than existing frameworks. OneFlow outperforms many well-known customized libraries built on top of the state-of-the-art frameworks.
  arXiv  Detail & Related papers  (2021-10-28T11:32:14Z)
• RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem [37.38316954355031]
  We re-examine the challenges posed by distributed reinforcement learning. We show that viewing RL as a dataflow problem leads to highly composable and performant implementations. We propose RLlib Flow, a hybrid actor-dataflow programming model for distributed RL.
  arXiv  Detail & Related papers  (2020-11-25T13:28:16Z)
• Training Recommender Systems at Scale: Communication-Efficient Model and Data Parallelism [56.78673028601739]
  We propose a compression framework called Dynamic Communication Thresholding (DCT) for communication-efficient hybrid training. DCT reduces communication by at least $100times$ and $20times$ during DP and MP, respectively. It improves end-to-end training time for a state-of-the-art industrial recommender model by 37%, without any loss in performance.
  arXiv  Detail & Related papers  (2020-10-18T01:44:42Z)
• Scheduling Policy and Power Allocation for Federated Learning in NOMA Based MEC [21.267954799102874]
  Federated learning (FL) is a highly pursued machine learning technique that can train a model centrally while keeping data distributed. We propose a new scheduling policy and power allocation scheme using non-orthogonal multiple access (NOMA) settings to maximize the weighted sum data rate. Simulation results show that the proposed scheduling and power allocation scheme can help achieve a higher FL testing accuracy in NOMA based wireless networks.
  arXiv  Detail & Related papers  (2020-06-21T23:07:41Z)
• Model Fusion via Optimal Transport [64.13185244219353]
  We present a layer-wise model fusion algorithm for neural networks. We show that this can successfully yield "one-shot" knowledge transfer between neural networks trained on heterogeneous non-i.i.d. data.
  arXiv  Detail & Related papers  (2019-10-12T22:07:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.