What it does
The publisher describes RWKV as an RNN and Transformer hybrid with O(n) inference, linear time and unlimited context, and no KV cache. Training runs in parallel like GPT, while inference runs sequentially like an RNN.
The publisher states that RWKV is a Linux Foundation AI project, that RWKV-7 was released in March 2025, and that the architecture is used in production at Windows, Office and NeMo.
The skill is published by davila7 under the MIT license.
Limitations and requirements
The publisher lists models up to 14B parameters.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 26
model-architecture-rwkv
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.
v1.0.0As shown on www.aitmpl.com when we last read it