[v1] Add Whisper model support (encoder-decoder) (#21088)

Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: NickLucche <nlucches@redhat.com>

vllm/v1/engine/processor.py

@@ -325,7 +325,6 @@ class Processor:
     ) -> tuple[Optional[str], EngineCoreRequest]:
 
         # TODO(woosuk): Support pooling models.
-        # TODO(woosuk): Support encoder-decoder models.
         self._validate_lora(lora_request)
         self._validate_params(params, lora_request)
         if trace_headers is not None:
@@ -384,10 +383,6 @@ class Processor:
 
         encoder_inputs, decoder_inputs = split_enc_dec_inputs(processed_inputs)
 
-        # TODO: Impl encoder-decoder
-        if encoder_inputs is not None:
-            raise NotImplementedError
-
         sampling_params = None
         pooling_params = None
         if isinstance(params, SamplingParams):