If you run into a problem and don’t find an answer here, feel free to reach out in our Discord community. We can even debug the issue with you over voice chat, or you can book a call with our engineers ❤️.
iOS app crashes
iOS app crashes
Each model may consume a significant amount of RAM, so it’s important to keep only one session loaded at a time. For iOS apps, we recommend adding the Increased Memory Capability entitlement to ensure your app can allocate the required memory.
It takes a long time to get the first token
It takes a long time to get the first token
The
Session
’s load
method loads the model weights into memory. A common practice is to keep one loaded session instance for the entire application lifecycle. After loading, you can run the same session multiple times. Don’t load a new session for each request.