# ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation

arXiv: https://arxiv.org/abs/2406.14088 · HTML: https://mlsanity.com/paper/2406.14088/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 39 of its 59 references that are in the map.
- First posted on arXiv 20 Jun 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 30 of 39)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM](https://mlsanity.com/paper/2104.04473/) (2021)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [ZeRO-Offload: Democratizing Billion-Scale Model Training](https://mlsanity.com/paper/2101.06840/) (2021)
- [ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning](https://mlsanity.com/paper/2104.07857/) (2021)
- [ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models](https://mlsanity.com/paper/2310.10505/) (2023)
- [Beyond Data and Model Parallelism for Deep Neural Networks](https://mlsanity.com/paper/1807.05358/) (2018)
- [S-LoRA: Serving Thousands of Concurrent LoRA Adapters](https://mlsanity.com/paper/2311.03285/) (2023)
- [Full Parameter Fine-tuning for Large Language Models with Limited Resources](https://mlsanity.com/paper/2306.09782/) (2023)
- [PipeDream: Fast and Efficient Pipeline Parallel DNN Training](https://mlsanity.com/paper/1806.03377/) (2018)
- [MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs](https://mlsanity.com/paper/2402.15627/) (2024)

## Built on by (most cited first, 30 of 37)

- [Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning](https://mlsanity.com/paper/2504.03380/) (2025)
- [OpenClaw-RL: Train Any Agent Simply by Talking](https://mlsanity.com/paper/2603.10165/) (2026)
- [On Designing Effective RL Reward at Training Time for LLM Reasoning](https://mlsanity.com/paper/2410.15115/) (2024)
- [Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL](https://mlsanity.com/paper/2505.10832/) (2025)
- [LLaDA2.1: Speeding Up Text Diffusion via Token Editing](https://mlsanity.com/paper/2602.08676/) (2026)
- [Optimizing RLHF Training for Large Language Models with Stage Fusion](https://mlsanity.com/paper/2409.13221/) (2024)
- [Laminar: A Scalable Asynchronous RL Post-Training Framework](https://mlsanity.com/paper/2510.12633/) (2025)
- [Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning](https://mlsanity.com/paper/2511.14617/) (2025)
- [AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent](https://mlsanity.com/paper/2512.20745/) (2025)
- [AgentV-RL: Scaling Reward Modeling with Agentic Verifier](https://mlsanity.com/paper/2604.16004/) (2026)
- [Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter](https://mlsanity.com/paper/2511.16665/) (2025)
- [OckBench: Measuring the Efficiency of LLM Reasoning](https://mlsanity.com/paper/2511.05722/) (2025)
- [MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Cluster](https://mlsanity.com/paper/2507.19017/) (2025)
- [AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs](https://mlsanity.com/paper/2511.00796/) (2025)
- [SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling](https://mlsanity.com/paper/2603.23414/) (2026)
- [7B Fully Open Source Moxin-LLM/VLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement](https://mlsanity.com/paper/2412.06845/) (2024)
- [Spend Your Rollouts Where It Counts: Rollout Allocation for Group-Based RL Post-Training](https://mlsanity.com/paper/2605.26606/) (2026)
- [A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directions](https://mlsanity.com/paper/2504.09100/) (2025)
- [TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training](https://mlsanity.com/paper/2604.09107/) (2026)
- [Libra: Efficient Resource Management for Agentic RL Post-Training](https://mlsanity.com/paper/2606.03077/) (2026)
- [GUI Agents with Reinforcement Learning: Toward Digital Inhabitants](https://mlsanity.com/paper/2604.27955/) (2026)
- [SDA: Steering-Driven Distribution Alignment for Open LLMs without Fine-Tuning](https://mlsanity.com/paper/2511.16324/) (2025)
- [Role-Based Fault Tolerance System for LLM RL Post-Training](https://mlsanity.com/paper/2512.22492/) (2025)
- [DynaResize: Runtime GPU Reallocation for Disaggregated LLM Post-Training](https://mlsanity.com/paper/2607.22614/) (2026)
- [SpecRoll: Fast-Slow Verifier-Feedback Adaptation for Speculative Reinforcement Learning Rollouts](https://mlsanity.com/paper/2608.04962/) (2026)
- [JigsawRL: Assembling RL Pipelines for Efficient LLM Post-Training](https://mlsanity.com/paper/2604.23838/) (2026)
- [AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs](https://mlsanity.com/paper/2605.15565/) (2026)
- [Nereus: Adaptive Parallelism for LLM Post-Training](https://mlsanity.com/paper/2609.34645/) (2026)
- [Balancing Robustness and Efficiency in Embedded DNNs Through Activation Function Selection](https://mlsanity.com/paper/2504.05119/) (2025)
- [Physio-DPO: Aligning Large Language Models with the Protein Energy Landscape to Eliminate Structural Hallucinations](https://mlsanity.com/paper/2601.00647/) (2026)

## Abstract (arXiv)

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for empowering large language model (LLM) applications. Compared with the supervised training process of LLMs, the RLHF training process is much more sophisticated, requiring a diverse range of computation workloads with intricate dependencies between multiple LLM instances. Therefore, simply adopting the fixed parallelization strategies from supervised training for LLMs can be insufficient for RLHF and result in low training efficiency. To overcome this limitation, we propose a novel technique named parameter ReaLlocation, which dynamically adapts the parallelization strategies for different workloads during training by redistributing LLM parameters across the training cluster. Building upon this idea, we introduce ReaL, a pioneering system for efficient RLHF training. ReaL introduces the concept of an execution plan, which defines a fine-grained resource allocation and parallelization strategy particularly designed for RLHF training. Based on this concept, ReaL employs a tailored search algorithm with a lightweight run-time estimator to automatically discover an efficient execution plan for an instance of RLHF experiment. Subsequently, the runtime engine deploys the selected plan by effectively parallelizing computations and redistributing parameters. We evaluate ReaL on the LLaMA models with up to 70 billion parameters and 128 GPUs. The experimental results demonstrate that ReaL achieves speedups of up to 3.58× compared to baseline methods. Furthermore, the execution plans generated by ReaL exhibit an average of 81% performance improvement over heuristic approaches based on Megatron-LM in the long-context scenario. The source code of ReaL is publicly available at https://github.com/openpsi-project/ReaLHF .