Design guide RNAs, predict off-target effects, simulate base and prime editing — with complete audit trails for regulatory compliance.
Eldric runs on any GPU — from a single RTX 3090 to NVIDIA H100/H200 datacenter cards. Connect labs, datacenters, and remote researchers into one cluster that spans cities or continents. Workers register through the Edge TLS gateway over the internet, or use the built-in tunnel for NAT traversal — no VPN needed. Adding a node is one command: the worker auto-registers and is immediately available for inference.
Train xLSTM on CRISPR outcome datasets for editing efficiency prediction. The model learns sequence context around the cut site (PAM + spacer + flanking) to predict on-target activity and off-target risk.
Sepp Hochreiter's xLSTM extended with Transformer layers for domain-specific tasks.
All endpoints are served by the Science Worker (:8897). Requests are routed through the Edge server for TLS and authentication in production.
Learn how to split large models across multiple workers with pipeline parallelism.
Distributed Inference Docs