LeMo: Enabling LEss Token Involvement for MOre Context Fine-tuning

• URL: http://arxiv.org/abs/2501.09767v1
• Date: Wed, 15 Jan 2025 05:17:12 GMT
• Title: LeMo: Enabling LEss Token Involvement for MOre Context Fine-tuning
• Authors: Tuowei Wang, Xingyu Chen, Kun Li, Ting Cao, Ju Ren, Yaoxue Zhang,
• Abstract summary: LeMo is a new LLM fine-tuning system that exploits a new token-level sparsity mechanism inherent in long-context scenarios. LeMo reduces memory consumption by up to 1.93x and achieves up to 1.36x speedups, outperforming state-of-the-art fine-tuning systems.
• Score: 38.35238373706948
• License:
• Abstract: The escalating demand for long-context applications has intensified the necessity of extending the LLM context windows. Despite recent fine-tuning approaches successfully expanding context lengths, their high memory footprints, especially for activations, present a critical practical limitation. Current parameter-efficient fine-tuning methods prioritize reducing parameter update overhead over addressing activation memory constraints. Similarly, existing sparsity mechanisms improve computational efficiency but overlook activation memory optimization due to the phenomenon of Shadowy Activation. In this paper, we propose LeMo, the first LLM fine-tuning system that explores and exploits a new token-level sparsity mechanism inherent in long-context scenarios, termed Contextual Token Sparsity. LeMo minimizes redundant token involvement by assessing the informativeness of token embeddings while preserving model accuracy. Specifically, LeMo introduces three key techniques: (1) Token Elimination, dynamically identifying and excluding redundant tokens across varying inputs and layers. (2) Pattern Prediction, utilizing well-trained predictors to approximate token sparsity patterns with minimal overhead. (3) Kernel Optimization, employing permutation-free and segment-based strategies to boost system performance. We implement LeMo as an end-to-end fine-tuning system compatible with various LLM architectures and other optimization techniques. Comprehensive evaluations demonstrate that LeMo reduces memory consumption by up to 1.93x and achieves up to 1.36x speedups, outperforming state-of-the-art fine-tuning systems.

Related papers

• How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization [15.434072331989878]
  Large Language Models (LLMs) exhibit strong general language capabilities. Fine-tuning these models on domain-specific tasks often leads to catastrophic forgetting, where the model overwrites or loses essential knowledge acquired during pretraining. We propose a novel approach to compute the element-wise importance of model parameters crucial for preserving general knowledge during fine-tuning.
  arXiv  Detail & Related papers  (2025-01-23T13:54:53Z)
• Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
  Large language models (LLMs) have significantly improved language understanding and generation capabilities. LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands. We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
  arXiv  Detail & Related papers  (2024-12-19T18:08:04Z)
• Activation Sparsity Opportunities for Compressing General Large Language Models [4.5624217435826]
  This work systematically investigates the tradeoff between enforcing activation sparsity and perplexity (accuracy) on state-of-the-art AI models. Our empirical analysis demonstrates that we can obtain around 50% of main memory and computing reductions for critical FFN components with negligible accuracy degradation.
  arXiv  Detail & Related papers  (2024-12-13T02:26:54Z)
• Ripple: Accelerating LLM Inference on Smartphones with Correlation-Aware Neuron Management [22.908079935647073]
  Large Language Models (LLMs) have achieved remarkable success across various domains, yet deploying them on mobile devices remains an arduous challenge. We propose Ripple, a novel approach that accelerates LLM inference on smartphones by optimizing neuron placement in flash memory. We demonstrate that Ripple achieves up to 5.93x improvements in I/O latency compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-10-25T03:01:19Z)
• Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design [59.00758127310582]
  We propose a novel framework Read-ME that transforms pre-trained dense LLMs into smaller MoE models. Our approach employs activation sparsity to extract experts. Read-ME outperforms other popular open-source dense models of similar scales.
  arXiv  Detail & Related papers  (2024-10-24T19:48:51Z)
• Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures [21.18741772731095]
  Zeroth-order (ZO) algorithms offer a promising alternative by approximating gradients using finite differences of function values. Existing ZO methods struggle to capture the low-rank gradient structure common in LLM fine-tuning, leading to suboptimal performance. This paper proposes a low-rank ZO algorithm (LOZO) that effectively captures this structure in LLMs.
  arXiv  Detail & Related papers  (2024-10-10T08:10:53Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning on Large-Language Models. We learn the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model. Our method operates for 2.7 hours with around 35GB memory for the 13B models on a single A100 GPU.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping [49.66872823080736]
  Autoregressive Large Language Models (e.g., LLaMa, GPTs) are omnipresent achieving remarkable success in language understanding and generation. To mitigate overload incurred during generation, several early-exit and layer-dropping strategies have been proposed. We propose FFN-SkipLLM, which is an input-adaptive feed-forward skipping strategy.
  arXiv  Detail & Related papers  (2024-04-05T02:35:43Z)
• Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark [166.40879020706151]
  This paper proposes a shift towards BP-free, zeroth-order (ZO) optimization as a solution for reducing memory costs during fine-tuning. Unlike traditional ZO-SGD methods, our work expands the exploration to a wider array of ZO optimization techniques. Our study unveils previously overlooked optimization principles, highlighting the importance of task alignment, the role of the forward gradient method, and the balance between algorithm complexity and fine-tuning performance.
  arXiv  Detail & Related papers  (2024-02-18T14:08:48Z)
• LLMCad: Fast and Scalable On-device Large Language Model Inference [11.103824752113148]
  Generative tasks, such as text generation and question answering, hold a crucial position in the realm of mobile applications. Currently, the execution of these generative tasks heavily depends on Large Language Models (LLMs) We introduce LLMCad, an on-device inference engine specifically designed for efficient generative Natural Language Processing (NLP) tasks.
  arXiv  Detail & Related papers  (2023-09-08T10:44:19Z)

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.