Upstream

Laya Python / PyTorch

The upstream reference implementation and Router. Start here for the canonical API, model checkpoints, fine-tuning, and cross-platform inference.

Reference behaviorPython servicesCUDA / CPUFine-tuning
Quickstart
pip install laya
Source
NandhaKishorM/laya

Warm and cold latency depend heavily on checkpoint, hardware, batching, and thread configuration.

Browse recipesView benchmarksExplore projects