Support embedding models in V1 (#16188)

Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>

vllm/v1/engine/logprobs.py

@@ -38,6 +38,7 @@ class LogprobsProcessor:
         tokenizer: Optional[AnyTokenizer],
         request: EngineCoreRequest,
     ) -> "LogprobsProcessor":
+        assert request.sampling_params is not None
         num_logprobs = request.sampling_params.logprobs
         num_prompt_logprobs = request.sampling_params.prompt_logprobs
         return cls(