TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs

• URL: http://arxiv.org/abs/2412.11242v2
• Date: Thu, 19 Dec 2024 10:33:13 GMT
• Title: TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs
• Authors: Lanxiang Hu, Tajana Rosing, Hao Zhang,
• Abstract summary: Specializing large language models (LLMs) for local deployment in domain-specific use cases is necessary for strong performance.<n>We develop TrimLLM based on the layer-wise specialization phenomenon we empirically observed and verified on contemporary LLMs.<n>We show it retains LLMs' capacity in specific domains and inference speedup achieves irrespective of hardware and deep learning frameworks.
• Score: 11.615399679746675
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Specializing large language models (LLMs) for local deployment in domain-specific use cases is necessary for strong performance while meeting latency and privacy constraints. However, conventional task-specific adaptation approaches do not show simultaneous memory saving and inference speedup at deployment time. Practical compression techniques like quantization and pruning require dedicated hardware or kernel support to achieve measured inference speedup. We develop TrimLLM based on the layer-wise specialization phenomenon we empirically observed and verified on contemporary LLMs. TrimLLM reduces the depth of LLMs via progressive layer dropping. We show it retains LLMs' capacity in specific domains and achieves inference speedup irrespective of hardware and deep learning frameworks. We evaluated TrimLLM on LLMs of various sizes for inference; models adapted on medical, legal, and financial datasets all demonstrate $2.1-5.7\times$ inference speedup on consumer GPUs and up to $3.1\times$ speedup on A100 when compared to state-of-the-art model compression algorithms, with no loss in accuracy at 50$\sim$60\% model compression ratio.

Related papers

• Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints [14.341123057506827]
  Large Language Models (LLMs) are indispensable in today's applications, but their inference procedure demands significant computational resources. This paper formulates LLM inference optimization as a multi-stage online scheduling problem. We develop a fluid dynamics approximation to provide a tractable benchmark that guides algorithm design.
  arXiv  Detail & Related papers  (2025-04-15T16:00:21Z)
• Token-Efficient Long Video Understanding for Multimodal LLMs [101.70681093383365]
  STORM is a novel architecture incorporating a dedicated temporal encoder between the image encoder and the Video-LLMs. We show that STORM achieves state-of-the-art results across various long video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-03-06T06:17:38Z)
• QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache [67.84112700032007]
  Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings. In these scenarios, the Key-Value ( KV) cache is the primary bottleneck in terms of both GPU memory and latency. We propose a novel self-speculative decoding framework, QuantSpec, where the draft model shares the architecture of the target model but employs a hierarchical 4-bit quantized KV cache and 4-bit quantized weights for acceleration.
  arXiv  Detail & Related papers  (2025-02-05T20:43:48Z)
• FASP: Fast and Accurate Structured Pruning of Large Language Models [24.185245582500876]
  We introduce FASP (Fast and Accurate Structured Pruning), a novel structured pruning framework for large language models (LLMs) FASP employs a distinctive pruning structure that interlinks sequential layers, allowing for the removal of columns in one layer while simultaneously eliminating corresponding rows in the preceding layer without incurring additional performance loss. We evaluate FASP on the OPT and LLaMA model families, demonstrating superior performance in terms of perplexity and accuracy on downstream tasks compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-01-16T09:38:39Z)
• Progressive Mixed-Precision Decoding for Efficient LLM Inference [49.05448842542558]
  We introduce Progressive Mixed-Precision Decoding (PMPD) to address the memory-boundedness of decoding. PMPD achieves 1.4$-$12.2$times$ speedup in matrix-vector multiplications over fp16 models. Our approach delivers a throughput gain of 3.8$-$8.0$times$ over fp16 models and up to 1.54$times$ over uniform quantization approaches.
  arXiv  Detail & Related papers  (2024-10-17T11:46:33Z)
• SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration [10.970637831760136]
  Speculative decoding (SD) has emerged as a widely used paradigm to accelerate the inference of large language models (LLMs) We introduce SWIFT, an on-the-fly self-speculative decoding algorithm that adaptively selects intermediate layers of LLMs to skip during inference. We show that SWIFT can achieve over a 1.3x-1.6x speedup while preserving the original distribution of the generated text.
  arXiv  Detail & Related papers  (2024-10-09T14:15:30Z)
• Mixture of Attentions For Speculative Decoding [17.344416130742232]
  Speculative decoding (SD) leverages smaller models to efficiently propose future tokens, which are then verified by the Large Language Models in parallel. We identify several limitations of SD models including the lack of on-policyness during training and partial observability. We propose a more grounded architecture for small models by introducing a Mixture of Attentions for SD.
  arXiv  Detail & Related papers  (2024-10-04T10:25:52Z)
• Search for Efficient Large Language Models [52.98684997131108]
  Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Weight pruning, quantization, and distillation have been embraced to compress LLMs, targeting memory reduction and inference acceleration. Most model compression techniques concentrate on weight optimization, overlooking the exploration of optimal architectures.
  arXiv  Detail & Related papers  (2024-09-25T21:32:12Z)
• On the Compressibility of Quantized Large Language Models [13.443384050034922]
  Large Language Models (LLMs) are deployed on edge or mobile devices to offer enhanced data privacy and real-time processing capabilities. LLMs may still be too big to fit entirely into the limited memory of edge or mobile devices and have to be partially loaded from the storage to complete the inference. We study applying data compression techniques to reduce data movement and thus speed up the inference of quantized LLM on memory-constrained devices.
  arXiv  Detail & Related papers  (2024-03-03T03:27:07Z)
• BiLLM: Pushing the Limit of Post-Training Quantization for LLMs [53.31402059062365]
  BiLLM is a groundbreaking 1-bit post-training quantization scheme tailored for pretrained large language models. It achieves for the first time high-accuracy inference (e.g. 8.41 perplexity on LLaMA2-70B) with only 1.08-bit weights across various LLMs families.
  arXiv  Detail & Related papers  (2024-02-06T09:26:34Z)
• TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models [52.454274602380124]
  Diffusion models heavily depend on the time-step $t$ to achieve satisfactory multi-round denoising. We propose a Temporal Feature Maintenance Quantization (TFMQ) framework building upon a Temporal Information Block. Powered by the pioneering block design, we devise temporal information aware reconstruction (TIAR) and finite set calibration (FSC) to align the full-precision temporal features.
  arXiv  Detail & Related papers  (2023-11-27T12:59:52Z)
• Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt [96.24800696597707]
  We introduce a new perspective to optimize this trade-off by prompting compressed models. We propose a soft prompt learning method where we expose the compressed model to the prompt learning process. Our experimental analysis suggests our soft prompt strategy greatly improves the performance of the 8x compressed LLaMA-7B model.
  arXiv  Detail & Related papers  (2023-05-17T20:45:13Z)

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.