Card: add RunPod deploy section

README.md

@@ -71,6 +71,25 @@ q = fe.embed_text("a dog on a beach")
 score = float(q @ v)                       # cosine, both unit-norm
 ```
 
+## Deploy on RunPod
+
+[![Deploy on RunPod](https://api.runpod.io/badge/Eximius-Labs/k3-vision)](https://www.runpod.io/console/hub/Eximius-Labs/k3-vision)
+
+One-click deploy the endpoint from the
+[RunPod Hub](https://www.runpod.io/console/hub/Eximius-Labs/k3-vision) (serverless,
+scales to zero when idle). Once it is running, call it:
+
+```bash
+curl -s https://api.runpod.ai/v2/<ENDPOINT_ID>/runsync \
+  -H "Authorization: Bearer $RUNPOD_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{"input": {"image": "<https url | data-uri | base64>"}}'
+```
+
+Kimi K3 is gated, so set `HF_TOKEN` (with the K3 license accepted) on the endpoint.
+Returns 2048-d vectors in the fusion-embedding-2 text space; query them with text
+through the fusion-embedding-2 endpoint.
+
 ## How it works
 
 1. Kimi K3's MoonViT-V2 vision tower (frozen) encodes an image into patch tokens (1024-d).