PyTorch12 min read
Beyond the KV cache: Training and serving i14’s Laplace 3B linear attention model on AWS Trainium2 with native PyTorch
Learn how i14 trained and served Laplace 3B, a linear attention model, on AWS Trainium2 using native PyTorch. Its recurrent state stays fixed at 29.5 MB per sequence regardless of context length, avoiding the growing key-value cache of transformer models and keeping serving memory predictable.
By Kevin ShabahangAWS ML Blog

Read the full story
Originally published by AWS ML Blog on Oct 20, 2026.
Comments
Sign in to join the discussion.