Baihui Liu

Wanyang Hong, Zhaoning Zhang, Yi Chen et al.

Large Language Models (LLMs) have achieved remarkable performance on single-turn tasks, yet their effectiveness deteriorates in multi-turn conversations. We define this phenomenon as cumulative contextual decay - a progressive degradation of contextual integrity caused by attention pollution, dilution, and drift. To address this challenge, we propose Rhea (Role-aware Heuristic Episodic Attention), a novel framework that decouples conversation history into two functionally independent memory modules: (1) an Instructional Memory (IM) that persistently stores high-fidelity global constraints via a structural priority mechanism, and (2) an Episodic Memory (EM) that dynamically manages user-model interactions via asymmetric noise control and heuristic context retrieval. During inference, Rhea constructs a high signal-to-noise context by applying its priority attention: selectively integrating relevant episodic information while always prioritizing global instructions. To validate this approach, experiments on multiple multi-turn conversation benchmarks - including MT-Eval and Long-MT-Bench+ - show that Rhea mitigates performance decay and improves overall accuracy by 1.04 points on a 10-point scale (a 16% relative gain over strong baselines). Moreover, Rhea maintains near-perfect instruction fidelity (IAR > 8.1) across long-horizon interactions. These results demonstrate that Rhea provides a principled and effective framework for building more precise, instruction-consistent conversational LLMs.

Kaiyuan Tian, Yu Tang, Gongqingjian Jiang et al.

Full-parameter fine-tuning of large language models is constrained by substantial GPU memory requirements. Low-rank adaptation methods mitigate this challenge by updating only a subset of parameters. However, these approaches often limit model expressiveness and yield lower performance than full-parameter fine-tuning. Layer-wise fine-tuning methods have emerged as an alternative, enabling memory-efficient training through static layer importance sampling strategies. However, these methods overlook variations in layer importance across tasks and training stages, resulting in suboptimal performance on downstream tasks. To address these limitations, we propose GRASS, a gradient-based adaptive layer-wise importance sampling framework. GRASS utilizes mean gradient norms as a task-aware and training-stage-aware metric for estimating layer importance. Furthermore, GRASS adaptively adjusts layer sampling probabilities through an adaptive training strategy. We also introduce a layer-wise optimizer state offloading mechanism that overlaps computation and communication to further reduce memory usage while maintaining comparable training throughput. Extensive experiments across multiple models and benchmarks demonstrate that GRASS consistently outperforms state-of-the-art methods, achieving an average accuracy improvement of up to 4.38 points and reducing memory usage by up to 19.97\%.

Baihui Liu, Kaiyuan Tian, Wei Wang et al.

Mixture-of-Experts (MoE) has become a dominant architecture for scaling large language models due to their sparse activation mechanism. However, the substantial number of expert activations creates a critical latency bottleneck during inference, especially in resource-constrained deployment scenarios. Existing approaches that reduce expert activations potentially lead to severe model performance degradation. In this work, we introduce the concept of \emph{activation budget} as a constraint on the number of expert activations and propose Alloc-MoE, a unified framework that optimizes budget allocation coordinately at both the layer and token levels to minimize performance degradation. At the layer level, we introduce Alloc-L, which leverages sensitivity profiling and dynamic programming to determine the optimal allocation of expert activations across layers. At the token level, we propose Alloc-T, which dynamically redistributes activations based on routing scores, optimizing budget allocation without increasing latency. Extensive experiments across multiple MoE models demonstrate that Alloc-MoE maintains model performance under a constrained activation budget. Especially, Alloc-MoE achieves $1.15\times$ prefill and $1.34\times$ decode speedups on DeepSeek-V2-Lite at half of the original budget.

Kaiyuan Tian, Linbo Qiao, Baihui Liu et al.

Scientific research faces high costs and inefficiencies with traditional methods, but the rise of deep learning and large language models (LLMs) offers innovative solutions. This survey reviews transformer-based LLM applications across scientific fields such as biology, medicine, chemistry, and meteorology, underscoring their role in advancing research. However, the continuous expansion of model size has led to significant memory demands, hindering further development and application of LLMs for science. This survey systematically reviews and categorizes memory-efficient pre-training techniques for large-scale transformers, including algorithm-level, system-level, and hardware-software co-optimization. Using AlphaFold 2 as an example, we demonstrate how tailored memory optimization methods can reduce storage needs while preserving prediction accuracy. By bridging model efficiency and scientific application needs, we hope to provide insights for scalable and cost-effective LLM training in AI for science.

Zhixin Ou, Peng Liang, Jianchen Han et al.

Dynamic sequences with varying lengths have been widely used in the training of Transformer-based large language models (LLMs). However, current training frameworks adopt a pre-defined static parallel strategy for these sequences, causing neither communication-parallelization cancellation on short sequences nor out-of-memory on long sequences. To mitigate these issues, we propose ParaDySe, a novel adaptive Parallel strategy switching framework for Dynamic Sequences. ParaDySe enables on-the-fly optimal strategy adoption according to the immediate input sequence. It first implements the modular function libraries for parallel strategies with unified tensor layout specifications, and then builds sequence-aware memory and time cost models with hybrid methods. Guided by cost models, ParaDySe selects optimal layer-wise strategies for dynamic sequences via an efficient heuristic algorithm. By integrating these techniques together, ParaDySe achieves seamless hot-switching of optimal strategies through its well-designed function libraries. We compare ParaDySe with baselines on representative LLMs under datasets with sequence lengths up to 624K. Experimental results indicate that ParaDySe addresses OOM and CPC bottlenecks in LLM training by systematically integrating long-sequence optimizations with existing frameworks.