Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.23292 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918108178939904 |
|---|---|
| author | Skerry-Ryan, RJ Salazar, Julian Mariooryad, Soroosh Kao, David Stanton, Daisy Battenberg, Eric Shannon, Matt Weiss, Ron J. Scheibler, Robin Rothfuss, Jonas Bagby, Tom |
| author_facet | Skerry-Ryan, RJ Salazar, Julian Mariooryad, Soroosh Kao, David Stanton, Daisy Battenberg, Eric Shannon, Matt Weiss, Ron J. Scheibler, Robin Rothfuss, Jonas Bagby, Tom |
| contents | We introduce a neural network layer API and library for sequence modeling, designed for easy creation of sequence models that can be executed both layer-by-layer (e.g., teacher-forced training) and step-by-step (e.g., autoregressive sampling). To achieve this, layers define an explicit representation of their state over time (e.g., a Transformer KV cache, a convolution buffer, an RNN hidden state), and a step method that evolves that state, tested to give identical results to a stateless layer-wise invocation. This and other aspects of the SequenceLayers contract enables complex models to be immediately streamable, mitigates a wide range of common bugs arising in both streaming and parallel sequence processing, and can be implemented in any deep learning library. A composable and declarative API, along with a comprehensive suite of layers and combinators, streamlines the construction of production-scale models from simple streamable components while preserving strong correctness guarantees. Our current implementations of SequenceLayers (JAX, TensorFlow 2) are available at https://github.com/google/sequence-layers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23292 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SequenceLayers: Sequence Processing and Streaming Neural Networks Made Easy Skerry-Ryan, RJ Salazar, Julian Mariooryad, Soroosh Kao, David Stanton, Daisy Battenberg, Eric Shannon, Matt Weiss, Ron J. Scheibler, Robin Rothfuss, Jonas Bagby, Tom Machine Learning Computation and Language Programming Languages Software Engineering Audio and Speech Processing We introduce a neural network layer API and library for sequence modeling, designed for easy creation of sequence models that can be executed both layer-by-layer (e.g., teacher-forced training) and step-by-step (e.g., autoregressive sampling). To achieve this, layers define an explicit representation of their state over time (e.g., a Transformer KV cache, a convolution buffer, an RNN hidden state), and a step method that evolves that state, tested to give identical results to a stateless layer-wise invocation. This and other aspects of the SequenceLayers contract enables complex models to be immediately streamable, mitigates a wide range of common bugs arising in both streaming and parallel sequence processing, and can be implemented in any deep learning library. A composable and declarative API, along with a comprehensive suite of layers and combinators, streamlines the construction of production-scale models from simple streamable components while preserving strong correctness guarantees. Our current implementations of SequenceLayers (JAX, TensorFlow 2) are available at https://github.com/google/sequence-layers. |
| title | SequenceLayers: Sequence Processing and Streaming Neural Networks Made Easy |
| topic | Machine Learning Computation and Language Programming Languages Software Engineering Audio and Speech Processing |
| url | https://arxiv.org/abs/2507.23292 |