Recurrent Drafter for Fast Speculative Decoding in Large Language Models

• URL: http://arxiv.org/abs/2403.09919v4
• Date: Wed, 09 Oct 2024 20:54:02 GMT
• Title: Recurrent Drafter for Fast Speculative Decoding in Large Language Models
• Authors: Yunfei Cheng, Aonan Zhang, Xuanyu Zhang, Chong Wang, Yi Wang,
• Abstract summary: We present Recurrent Drafter, an advanced speculative decoding approach. It achieves state-of-the-art speedup for large language models (LLMs) inference.
• Score: 18.342742904042673
• License:
• Abstract: We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves state-of-the-art speedup for large language models (LLMs) inference. The performance gains are driven by three key aspects: (1) leveraging a recurrent neural network (RNN) as the draft model conditioning on LLM's hidden states, (2) applying a dynamic tree attention algorithm over beam search results to eliminate duplicated prefixes in candidate sequences, and (3) training through knowledge distillation from the LLM. ReDrafter accelerates Vicuna inference in MT-Bench by up to 3.5x with a PyTorch implementation on Nvidia H100 GPUs. To demonstrate its practicality in production environments, we integrate ReDrafter into TensorRT-LLM, reaching up to 2.5x speedup on H100 GPUs. We also validated its effectiveness for on-device applications by implementing the approach in MLX and benchmarking performance on Metal GPUs in Apple Silicon chips, achieving up to 2.3x speedup.

Related papers

• MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention [36.49445805074941]
  MInference (Milliontokens Inference) is a sparse calculation method designed to accelerate pre-filling of long-sequence processing. We demonstrate that MInference effectively reduces inference latency by up to 10x for pre-filling on an A100, while maintaining accuracy.
  arXiv  Detail & Related papers  (2024-07-02T17:59:56Z)
• S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for Low-Memory GPUs [7.816840847892339]
  Speculative decoding (SD) has attracted a significant amount of research attention due to the substantial speedup it can achieve for LLM inference. We propose Skippy Simultaneous Speculative Decoding (or S3D), a cost-effective self-speculative SD method based on simultaneous multi-token decoding and mid-layer skipping. Our method has achieved one of the top performance-memory ratios while requiring minimal architecture changes and training data.
  arXiv  Detail & Related papers  (2024-05-30T17:54:35Z)
• Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment [56.44025052765861]
  Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs. We show a total speedup on CPUs for sparse-quantized LLaMA models of up to 8.6x.
  arXiv  Detail & Related papers  (2024-05-06T16:03:32Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)
• GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstruction [50.248694764703714]
  Unrolled neural networks have recently achieved state-of-the-art accelerated MRI reconstruction. These networks unroll iterative optimization algorithms by alternating between physics-based consistency and neural-network based regularization. We propose Greedy LEarning for Accelerated MRI reconstruction, an efficient training strategy for high-dimensional imaging settings.
  arXiv  Detail & Related papers  (2022-07-18T06:01:29Z)
• Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining [58.10436813430554]
  Mini-batch training of graph neural networks (GNNs) requires a lot of computation and data movement. We argue in favor of performing mini-batch training with neighborhood sampling in a distributed multi-GPU environment. We present a sequence of improvements to mitigate these bottlenecks, including a performance-engineered neighborhood sampler. We also conduct an empirical analysis that supports the use of sampling for inference, showing that test accuracies are not materially compromised.
  arXiv  Detail & Related papers  (2021-10-16T02:41:35Z)
• Large Batch Simulation for Deep Reinforcement Learning [101.01408262583378]
  We accelerate deep reinforcement learning-based training in visually complex 3D environments by two orders of magnitude over prior work. We realize end-to-end training speeds of over 19,000 frames of experience per second on a single and up to 72,000 frames per second on a single eight- GPU machine. By combining batch simulation and performance optimizations, we demonstrate that Point navigation agents can be trained in complex 3D environments on a single GPU in 1.5 days to 97% of the accuracy of agents trained on a prior state-of-the-art system.
  arXiv  Detail & Related papers  (2021-03-12T00:22:50Z)
• Applying GPGPU to Recurrent Neural Network Language Model based Fast Network Search in the Real-Time LVCSR [5.0555627833288]
  Recurrent Neural Network Language Models (RNNLMs) have started to be used in various fields of speech recognition. High computational complexity of RNNLMs has been a hurdle in applying the RNNLM to a real-time Large Vocabulary Continuous Speech Recognition.
  arXiv  Detail & Related papers  (2020-07-23T05:15:14Z)
• A Real-time Action Representation with Temporal Encoding and Deep Compression [115.3739774920845]
  We propose a new real-time convolutional architecture, called Temporal Convolutional 3D Network (T-C3D), for action representation. T-C3D learns video action representations in a hierarchical multi-granularity manner while obtaining a high process speed. Our method achieves clear improvements on UCF101 action recognition benchmark against state-of-the-art real-time methods by 5.4% in terms of accuracy and 2 times faster in terms of inference speed with a less than 5MB storage model.
  arXiv  Detail & Related papers  (2020-06-17T06:30:43Z)

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.