SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM

• URL: http://arxiv.org/abs/2406.06571v5
• Date: Fri, 23 Aug 2024 08:17:58 GMT
• Title: SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM
• Authors: Quandong Wang, Yuxuan Yuan, Xiaoyu Yang, Ruike Zhang, Kang Zhao, Wei Liu, Jian Luan, Daniel Povey, Bin Wang,
• Abstract summary: SUBLLM is an innovative architecture that extends the core decoder-only framework by incorporating subsampling, upsampling, and bypass modules. During training, SUBLLM increases speeds by 26% and cuts memory by 10GB per GPU. In inference, it boosts speeds by up to 37% and reduces memory by 1GB per GPU.
• Score: 24.65339628772433
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Large Language Models (LLMs) have achieved remarkable success in various fields, the efficiency of training and inference remains a major challenge. To address this issue, we propose SUBLLM, short for Subsampling-Upsampling-Bypass Large Language Model, an innovative architecture that extends the core decoder-only framework by incorporating subsampling, upsampling, and bypass modules. The subsampling modules are responsible for shortening the sequence, while the upsampling modules restore the sequence length, and the bypass modules enhance convergence. In comparison to LLaMA, the proposed SUBLLM exhibits significant enhancements in both training and inference speeds as well as memory usage, while maintaining competitive few-shot performance. During training, SUBLLM increases speeds by 26% and cuts memory by 10GB per GPU. In inference, it boosts speeds by up to 37% and reduces memory by 1GB per GPU. The training and inference speeds can be enhanced by 34% and 52% respectively when the context window is expanded to 8192. Our code is available at https://github.com/XiaoMi/subllm.

Related papers

• MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models [58.3342517278868]
  This paper describes the design of Mixed-precision AutoRegressive LINear kernels. It shows that batchsizes up to 16-32 can be supported with close to maximum ($4times$) quantization speedup. MarLIN accomplishes this via a combination of techniques, such as asynchronous memory access, complex task scheduling and pipelining.
  arXiv  Detail & Related papers  (2024-08-21T16:10:41Z)
• vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving [53.972175896814505]
  Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests.
  arXiv  Detail & Related papers  (2024-07-22T14:37:58Z)
• Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training [78.93900796545523]
  Mini-Sequence Transformer (MsT) is a methodology for highly efficient and accurate LLM training with extremely long sequences. MsT partitions input sequences and iteratively processes mini-sequences to reduce intermediate memory usage. integrated with the huggingface library, MsT successfully extends the maximum context length of Qwen, Mistral, and Gemma-2 by 12-24x.
  arXiv  Detail & Related papers  (2024-07-22T01:52:30Z)
• Efficiently Training 7B LLM with 1 Million Sequence Length on 8 GPUs [24.066283519769968]
  Large Language Models (LLMs) have been trained using extended context lengths to foster more creative applications. We propose MEMO, a novel framework for fine-grained activation memory management. We show that MEMO achieves an average of 2.42x and 2.26x MFU compared to Megatron-LM and DeepSpeed.
  arXiv  Detail & Related papers  (2024-07-16T18:59:49Z)
• FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models [24.030755262499994]
  FastMem is a novel method designed to enhance instruction fine-tuned large language models' context awareness. It maximizes the likelihood of the prompt before inference by updating only the last Feed-Forward Network (FFN) module. Our experiments demonstrate substantial gains in reading comprehension, text summarization and adherence to output structures.
  arXiv  Detail & Related papers  (2024-06-23T10:36:35Z)
• MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory [49.96019697955383]
  We introduce MemLLM, a novel method of enhancing knowledge capabilities by integrating a structured and explicit read-and-write memory module. Our experiments indicate that MemLLM enhances performance and interpretability, in language modeling general and in particular. We see MemLLM as an important step towards making LLMs more grounded and factual through memory augmentation.
  arXiv  Detail & Related papers  (2024-04-17T18:13:16Z)
• LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units [5.830814457423021]
  Transformer models have demonstrated high accuracy in numerous applications but have high complexity and lack sequential processing capability. We show how architectural modifications to a recurrent model can help push its performance toward Transformer models. We present a spiking version of this architecture, which introduces the benefit of states within the patch embedding and channel mixer modules.
  arXiv  Detail & Related papers  (2024-01-20T01:10:18Z)
• DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training [82.06732962485754]
  FlashAttention effectively reduces the quadratic peak memory usage to linear in training transformer-based large language models (LLMs) on a single GPU. We introduce DISTFLASHATTN, a memory-efficient attention mechanism optimized for long-context LLMs training. It achieves 1.67x and 1.26 - 1.88x speedup compared to recent Ring Attention and DeepSpeed-Ulysses.
  arXiv  Detail & Related papers  (2023-10-05T03:47:57Z)
• Full Parameter Fine-tuning for Large Language Models with Limited Resources [55.794732214059806]
  Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) but demand massive GPU resources for training. We propose a new computation, LOw-Memory Optimization (LOMO), which fuses the gradient and the parameter update in one step to reduce memory usage.
  arXiv  Detail & Related papers  (2023-06-16T11:37:15Z)

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.