diff --git a/llmfoundry/models/inference_api_wrapper/interface.py b/llmfoundry/models/inference_api_wrapper/interface.py index 6f06b262d2..a513654c18 100644 --- a/llmfoundry/models/inference_api_wrapper/interface.py +++ b/llmfoundry/models/inference_api_wrapper/interface.py @@ -49,7 +49,6 @@ def get_metrics(self, is_train: bool = False): def get_next_token_logit_tensor(self, prompt: str) -> Optional[torch.Tensor]: - # returns None if the inference API stopped early raise NotImplementedError def rebatch(self, batch: Batch):