# EPAS: Efficient Training with Progressive Activation Sharing

arXiv: https://arxiv.org/abs/2601.19089 · HTML: https://mlsanity.com/paper/2601.19089/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 43 of its 48 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Builds on (most cited first, 30 of 43)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [TinyLlama: An Open-Source Small Language Model](https://mlsanity.com/paper/2401.02385/) (2024)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [Reducing Transformer Depth on Demand with Structured Dropout](https://mlsanity.com/paper/1909.11556/) (2019)
- [A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations](https://mlsanity.com/paper/2308.06767/) (2023)
- [LLM in a flash: Efficient Large Language Model Inference with Limited Memory](https://mlsanity.com/paper/2312.11514/) (2023)
- [You Only Cache Once: Decoder-Decoder Architectures for Language Models](https://mlsanity.com/paper/2405.05254/) (2024)
- [Reducing Transformer Key-Value Cache Size with Cross-Layer Attention](https://mlsanity.com/paper/2405.12981/) (2024)
- [LLaMA Pro: Progressive LLaMA with Block Expansion](https://mlsanity.com/paper/2401.02415/) (2024)
- [SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks](https://mlsanity.com/paper/2402.09025/) (2024)
- [Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping](https://mlsanity.com/paper/2010.13369/) (2020)
- [What Matters in Transformers? Not All Attention is Needed](https://mlsanity.com/paper/2406.15786/) (2024)
- [Layer-Condensed KV Cache for Efficient Inference of Large Language Models](https://mlsanity.com/paper/2405.10637/) (2024)
- [Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application](https://mlsanity.com/paper/2407.01885/) (2024)
- [FreezeOut: Accelerate Training by Progressively Freezing Layers](https://mlsanity.com/paper/1706.04983/) (2017)
- [Flextron: Many-in-One Flexible Large Language Model](https://mlsanity.com/paper/2406.10260/) (2024)
- [SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models](https://mlsanity.com/paper/2401.08295/) (2024)
- [Automated Progressive Learning for Efficient Training of Vision Transformers](https://mlsanity.com/paper/2203.14509/) (2022)
- [SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation](https://mlsanity.com/paper/2410.03960/) (2024)
- [LazyFormer: Self Attention with Lazy Update](https://mlsanity.com/paper/2102.12702/) (2021)
- [AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models](https://mlsanity.com/paper/2403.13269/) (2024)
- [Time Sensitive Knowledge Editing through Efficient Finetuning](https://mlsanity.com/paper/2406.04496/) (2024)
- [SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training](https://mlsanity.com/paper/2407.06654/) (2024)

## Abstract (arXiv)

We present a novel method for Efficient training with Progressive Activation Sharing (EPAS). This method bridges progressive training paradigm with the phenomenon of redundant QK (or KV ) activations across deeper layers of transformers. EPAS gradually grows a sharing region during training by switching decoder layers to activation sharing mode. This results in throughput increase due to reduced compute. To utilize deeper layer redundancy, the sharing region starts from the deep end of the model and grows towards the shallow end. The EPAS trained models allow for variable region lengths of activation sharing for different compute budgets during inference. Empirical evaluations with QK activation sharing in LLaMA models ranging from 125M to 7B parameters show up to an 11.1% improvement in training throughput and up to a 29% improvement in inference throughput while maintaining similar loss curve to the baseline models. Furthermore, applying EPAS in continual pretraining to transform TinyLLaMA into an attention-sharing model yields up to a 10% improvement in average accuracy over state-of-the-art methods, emphasizing the significance of progressive training in cross layer activation sharing models.