arctic_inference/vllm/spec_dec/arctic_speculator.py [329:340]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if num_predict_tokens > self.max_speculative_tokens:
            raise ValueError(f"Max speculative tokens for model is "
                             f"{self.max_speculative_tokens}, but "
                             f"{num_predict_tokens} were requested")

        # b x 1 x d
        previous_hidden_states = previous_hidden_states.unsqueeze(1)

        # b x 1
        last_tokens = input_ids.unsqueeze(1)

        batch_size = input_ids.size(0)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



arctic_inference/vllm/spec_dec/arctic_speculator.py [759:770]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if num_predict_tokens > self.max_speculative_tokens:
            raise ValueError(f"Max speculative tokens for model is "
                             f"{self.max_speculative_tokens}, but "
                             f"{num_predict_tokens} were requested")

        # b x 1 x d
        previous_hidden_states = previous_hidden_states.unsqueeze(1)

        # b x 1
        last_tokens = input_ids.unsqueeze(1)

        batch_size = input_ids.size(0)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -