Gated Linear Attention Transformers with Hardware-Efficient Training
Transformers with linear attention allow for efficient parallel training but can simultaneously be formulated as an RNN with 2D (matrix-valued) hidden states, thus enjoying linear-time inference complexity. However, linear attention generally underperforms ordinary softmax attention. Moreover, current implementations of linear attention lack I/O-awareness and are thus slower than highly optimized implementations of softmax attention. This work describes a hardware-efficient algorithm for linear attention that trades off memory movement against parallelizability. The resulting implementation, dubbed FLASHLINEARATTENTION, is faster than FLASHATTENTION-2 (Dao, 2023) as a standalone layer even on short sequence lengths (e.g., 1K). We then generalize this algorithm to a more expressive variant of linear attention with data-dependent gates. When used as a replacement for the standard attention layer in Transformers, the resulting gated linear attention (GLA) Transformer is found to perform competitively against the LLaMA-architecture Transformer (Touvron et al., 2023) as well recent linear-time-inference baselines such as RetNet (Sun et al., 2023a) and Mamba (Gu & Dao, 2023) on moderate-scale language modeling experiments. GLA Transformer is especially effective at length generalization, enabling a model trained on 2K to generalize to sequences longer than 20K without significant perplexity degradations. For training speed, the GLA Transformer has higher throughput than a similarly-sized Mamba model.
Code (6)
Tasks
2kLanguage ModelingLanguage ModellingMambaMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Gated Slot Attention for Efficient Linear-Time Sequence Modeling
Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and dem…
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Recurrent neural networks (RNNs) have fast inference and scale efficiently on long sequences, but they are difficult to train and hard to scale. We propose Hawk, an RNN with gated linear recurrences, and Griffin, a hybri…
Language ModellingMambaGated Delta Networks: Improving Mamba2 with Delta Rule
Linear Transformers have gained attention as efficient alternatives to standard Transformers, but their performance in retrieval and long-context tasks has been limited. To address these limitations, recent work has expl…
Common Sense ReasoningLanguage ModelingLanguage ModellingLong-Context Understanding+1Parallelizing Linear Transformers with the Delta Rule over Sequence Length
Transformers with linear attention (i.e., linear transformers) and state-space models have recently been suggested as a viable linear-time alternative to transformers with softmax attention. However, these models still u…
Language ModelingLanguage ModellingMambaState Space ModelsMamba: Linear-Time Sequence Modeling with Selective State Spaces
Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as…
2D Pose EstimationCommon Sense ReasoningComputational EfficiencyLanguage Modeling+5