[BUGFIX] When skip_tokenize_init and multistep are set, execution crashes (vllm-project#12277)

Signed-off-by: maleksan85 <[email protected]>
Co-authored-by: maleksan85 <[email protected]>

Author: 2 people

vllm/engine/output_processor/multi_step.py

@@ -144,7 +144,7 @@ def process_outputs(self,
     def _process_decode_and_stop(self, seq: Sequence,
                                  sampling_params: SamplingParams) -> None:
         new_char_count = 0
-        if sampling_params.detokenize:
+        if sampling_params.detokenize and self.detokenizer:
             new_char_count = self.detokenizer.decode_sequence_inplace(
                 seq, sampling_params)