Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models

• URL: http://arxiv.org/abs/2503.05005v2
• Date: Mon, 10 Mar 2025 18:52:15 GMT
• Title: Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models
• Authors: Benyamin Jamialahmadi, Parsa Kavehzadeh, Mehdi Rezagholizadeh, Parsa Farinneya, Hossein Rajabzadeh, Aref Jafari, Boxing Chen, Marzieh S. Tahaei,
• Abstract summary: Balcony is a framework for depth-based dynamic inference.<n>It maintains the full model's performance while enabling real-time adaptation to different computational budgets.<n>Remarkably, we show that Balcony outperforms state-of-the-art methods such as Flextron and Layerskip.
• Score: 31.103832542711864
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Deploying large language models (LLMs) in real-world applications is often hindered by strict computational and latency constraints. While dynamic inference offers the flexibility to adjust model behavior based on varying resource budgets, existing methods are frequently limited by hardware inefficiencies or performance degradation. In this paper, we introduce Balcony, a simple yet highly effective framework for depth-based dynamic inference. By freezing the pretrained LLM and inserting additional transformer layers at selected exit points, Balcony maintains the full model's performance while enabling real-time adaptation to different computational budgets. These additional layers are trained using a straightforward self-distillation loss, aligning the sub-model outputs with those of the full model. This approach requires significantly fewer training tokens and tunable parameters, drastically reducing computational costs compared to prior methods. When applied to the LLaMA3-8B model, using only 0.2% of the original pretraining data, Balcony achieves minimal performance degradation while enabling significant speedups. Remarkably, we show that Balcony outperforms state-of-the-art methods such as Flextron and Layerskip as well as other leading compression techniques on multiple models and at various scales, across a variety of benchmarks.

Related papers

• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step. To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration. Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [70.91804882618243]
  This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.<n>We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge.<n>Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
  arXiv  Detail & Related papers  (2025-02-18T02:37:26Z)
• From Dense to Dynamic: Token-Difficulty Driven MoEfication of Pre-Trained LLMs [37.50902921493273]
  Training large language models (LLMs) for different inference constraints is computationally expensive.<n> DynaMoE adapts a pre-trained dense LLM to a token-difficulty-driven Mixture-of-Experts model with minimal fine-tuning cost.<n>Our method achieves similar aggregated accuracy across downstream tasks, despite using only $frac19textth$ of their fine-tuning cost.
  arXiv  Detail & Related papers  (2025-02-17T21:12:57Z)
• Transformer Layer Injection: A Novel Approach for Efficient Upscaling of Large Language Models [0.0]
  Transformer Layer Injection (TLI) is a novel method for efficiently upscaling large language models (LLMs) Our approach improves upon the conventional Depth Up-Scaling (DUS) technique by injecting new layers into every set of K layers.
  arXiv  Detail & Related papers  (2024-10-15T14:41:44Z)
• Pruning Large Language Models with Semi-Structural Adaptive Sparse Training [17.381160429641316]
  Adaptive Sparse Trainer (AST) is a novel and efficient retraining framework tailored for semi-structured sparse models.<n>AST reduces the perplexity and zero-shot accuracy gap between dense and 2:4 semi-structured sparse models to 0.6 and 1.16%, respectively.
  arXiv  Detail & Related papers  (2024-07-30T06:33:44Z)
• Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models [109.06052781040916]
  We introduce a technique to enhance the inference efficiency of parameter-shared language models. We also propose a simple pre-training technique that leads to fully or partially shared models. Results demonstrate the effectiveness of our methods on both autoregressive and autoencoding PLMs.
  arXiv  Detail & Related papers  (2023-10-19T15:13:58Z)
• ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models [70.45441031021291]
  Large Vision-Language Models (LVLMs) can understand the world comprehensively by integrating rich information from different modalities. LVLMs are often problematic due to their massive computational/energy costs and carbon consumption. We propose Efficient Coarse-to-Fine LayerWise Pruning (ECoFLaP), a two-stage coarse-to-fine weight pruning approach for LVLMs.
  arXiv  Detail & Related papers  (2023-10-04T17:34:00Z)
• COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models [16.586312156966635]
  Transformer-based pre-trained language models (PLMs) mostly suffer from excessive overhead despite their advanced capacity. Existing statically compressed models are unaware of the diverse complexities between input instances. We propose a collaborative optimization for PLMs that integrates static model compression and dynamic inference acceleration.
  arXiv  Detail & Related papers  (2022-10-27T15:06:40Z)
• A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness [11.35810118757863]
  Existing models that achieve state-of-the-art (SOTA) performance on both clean and adversarially-perturbed images rely on convolution operations conditioned with feature-wise linear modulation (FiLM) layers. We present a fast learnable once-for-all adversarial training (FLOAT) algorithm, which instead of the existing FiLM-based conditioning, presents a unique weight conditioned learning that requires no additional layer. In particular, we add scaled noise to the weight tensors that enables a trade-off between clean and adversarial performance.
  arXiv  Detail & Related papers  (2022-03-28T19:25:36Z)
• Dynamic Model Pruning with Feedback [64.019079257231]
  We propose a novel model compression method that generates a sparse trained model without additional overhead. We evaluate our method on CIFAR-10 and ImageNet, and show that the obtained sparse models can reach the state-of-the-art performance of dense models.
  arXiv  Detail & Related papers  (2020-06-12T15:07:08Z)

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.