Optional
Optional abort signal to stop the generation. This can also be used to stop during prompt processing. In this case, it will throw WllamaAbortError.
When processing input prompt, we don't need to get output tokens. Only used by llama_decode() Default: false
If true, return an AsyncIterable instead of a string
Optional abort signal to stop the generation. This can also be used to stop during prompt processing. In this case, it will throw WllamaAbortError.