Agent Skills: rwkv-architecture

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

transformersrnnlinear-time-inferencemodel-architecturelinux-foundation

architectureID: ovachiever/droid-tings/rwkv-architecture

Author

ovachiever

https://github.com/ovachiever View all skills

Repository

ovachiever/droid-tings

ovachieverLicense: NOASSERTION

Skill Files

Browse the full folder contents for rwkv-architecture.

Download Skill

Loading file tree…

Select a file to preview its contents.