Diagonal Batching Unlocks Parallelism In Recurrent Memory Transformers For Long Contexts | Awesome LLM Papers Contribute to Awesome LLM Papers

Awesome LLM Papers

A curated collection of research papers on Large Language Models (LLMs), transformers, prompting, fine-tuning, and multi-modal systems. Maintained by Sean Moran.

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

Diagonal Batching Unlocks Parallelism In Recurrent Memory Transformers For Long Contexts

Danil Sivtsov, Ivan Rodkin, Gleb Kuzmin, Yuri Kuratov, Ivan Oseledets . No Venue 2025

[Paper] [Paper]   Search on Google Scholar   Search on Semantic Scholar
Applications Memory & Context Model Architecture

Transformer models struggle with long-context inference due to their quadratic time and linear memory complexity. Recurrent Memory Transformers (RMTs) offer a solution by reducing the asymptotic cost to linear time and constant memory usage. However, their memory update mechanism leads to sequential execution, causing a performance bottleneck. We introduce Diagonal Batching, a scheduling scheme that unlocks parallelism across segments in RMTs while preserving exact recurrence. This approach eliminates the sequential constraint, enabling efficient GPU inference even for single long-context inputs without complex batching and pipelining techniques. Because the technique is purely a run-time computation reordering, existing RMT models adopt it with no retraining. Applied to a LLaMA-1B ARMT model, Diagonal Batching yields a 3.3x speedup over standard full-attention LLaMA-1B and a 1.8x speedup over the sequential RMT implementation on 131,072-token sequences. By removing sequential bottleneck, Diagonal Batching reduces inference cost and latency, thereby strengthening RMTs as a practical solution for real-world, long-context applications.

https://huggingface.co/discussions/paper/6842bc6955574a112d573421

Similar Work