diff --git a/backends/exllamav3/model.py b/backends/exllamav3/model.py index 69ee0d4..4f67fd3 100644 --- a/backends/exllamav3/model.py +++ b/backends/exllamav3/model.py @@ -624,7 +624,6 @@ class ExllamaV3Container(BaseModelContainer): return dict(zip_longest(top_tokens, cleaned_values)) - async def generate( self, request_id: str,