# An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training

arXiv: https://arxiv.org/abs/2312.11819 · HTML: https://mlsanity.com/paper/2312.11819/

## Key facts

- Cited by 13 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 34 of its 50 references that are in the map.
- First posted on arXiv 19 Dec 2023.

## 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 34)

- [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)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [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)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model](https://mlsanity.com/paper/2201.11990/) (2022)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers](https://mlsanity.com/paper/2206.01861/) (2022)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [Horovod: fast and easy distributed deep learning in TensorFlow](https://mlsanity.com/paper/1802.05799/) (2018)
- [Mesh-TensorFlow: Deep Learning for Supercomputers](https://mlsanity.com/paper/1811.02084/) (2018)
- [Alignment of Language Agents](https://mlsanity.com/paper/2103.14659/) (2021)
- [PipeDream: Fast and Efficient Pipeline Parallel DNN Training](https://mlsanity.com/paper/1806.03377/) (2018)
- [DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scales](https://mlsanity.com/paper/2308.01320/) (2023)
- [DAPPLE: A Pipelined Data Parallel Approach for Training Large Models](https://mlsanity.com/paper/2007.01045/) (2020)
- [Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training](https://mlsanity.com/paper/2110.14883/) (2021)
- [Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads](https://mlsanity.com/paper/1901.05758/) (2019)
- [ZeRO++: Extremely Efficient Collective Communication for Giant Model Training](https://mlsanity.com/paper/2306.10209/) (2023)

## Built on by (most cited first, 13 of 13)

- [Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning](https://mlsanity.com/paper/2503.15558/) (2025)
- [LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training](https://mlsanity.com/paper/2505.24034/) (2025)
- [ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation](https://mlsanity.com/paper/2406.14088/) (2024)
- [Laminar: A Scalable Asynchronous RL Post-Training Framework](https://mlsanity.com/paper/2510.12633/) (2025)
- [Introducing LongCat-Flash-Thinking: A Technical Report](https://mlsanity.com/paper/2509.18883/) (2025)
- [Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter](https://mlsanity.com/paper/2511.16665/) (2025)
- [DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training](https://mlsanity.com/paper/2604.26256/) (2026)
- [RLHFSpec: Breaking the Efficiency Bottleneck in RLHF Training via Adaptive Drafting](https://mlsanity.com/paper/2512.04752/) (2025)
- [WeChat-YATT: A Scalable, Simple, Efficient, and Production Ready Training Library](https://mlsanity.com/paper/2508.07970/) (2025)
- [AntDT: A Self-Adaptive Distributed Training Framework for Leader and Straggler Nodes](https://mlsanity.com/paper/2404.09679/) (2024)
- [Understanding and Alleviating Memory Consumption in RLHF for LLMs](https://mlsanity.com/paper/2410.15651/) (2024)
- [G-Core: A Simple, Scalable and Balanced RLHF Trainer](https://mlsanity.com/paper/2507.22789/) (2025)
- [How Fast Can Reward Models Score? A Systems Study of C++ and PyTorch Inference Runtimes for RLHF](https://mlsanity.com/paper/2607.19712/) (2026)

## Abstract (arXiv)

Recently, ChatGPT or InstructGPT like large language models (LLM) has made a significant impact in the AI world. Many works have attempted to reproduce the complex InstructGPT's training pipeline, namely Reinforcement Learning with Human Feedback (RLHF). However, the mainstream distributed RLHF training methods typically adopt a fixed model placement strategy, referred to as the Co-located strategy. This strategy treats all four interdependent models involved in RLHF as a single entity, distributing them across all devices and applying parallelism techniques designed for a single model, regardless of the workload heterogeneity inherent to each model. As a result, this strategy exacerbates the generation bottlenecks in the RLHF training and degrades the overall training efficiency. To address these issues, we propose a flexible model placement framework that offers two general and agile model placement strategies. The Interleaving strategy helps reduce memory redundancy and communication costs of RLHF training by placing models without dependencies on exclusive devices with careful orchestration. On the other hand, the Disaggregated strategy improves the throughput of model training by separating the training and inference runtime of the RLHF pipeline with additional shadow models. Furthermore, our framework provides a simple user interface and guidelines to easily and flexibly configure these strategies in various training scenarios. Our experiments have shown that our strategy can achieve notable improvements up to 11x, compared to the current state-of-the-art (SOTA) approaches. The results highlight the effectiveness and adaptability of our methods in accelerating the training of distributed RLHF.