i14 trains and deploys Laplace 3B linear attention model on AWS Trainium2
What happened
On 21 October 2026, the AWS Machine Learning Blog reported that i14 worked with AWS to port the linear attention model Laplace 3B to AWS Trainium2 via TorchNeuron Native, completing training and inference on the chip with native PyTorch while retaining its Gated Linear Attention design and Muon optimiser. The report did not disclose details such as training scale, duration, performance comparisons or a deployment timeline.
Written by AI from the reports · updated 3 h ago
Timeline
Follow the reports to see the event from each side.
- AWS Machine Learning BlogBeyond 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.
Heat of this event
Current heat 9·Peak in the comparable range 10（Oct 21 07:00）·Change over 24 hours in the comparable range –
The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.