Correct capitalisation: VLLM -> vLLM (#14562)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

vllm/v1/engine/core_client.py

@@ -255,7 +255,7 @@ class MPClient(EngineCoreClient):
         # TODO(rob): rather than killing the main process, we should
         # figure out how to raise an AsyncEngineDeadError and
         # handle at the API server level so we can return a better
-        # error code to the clients calling VLLM.
+        # error code to the clients calling vLLM.
         def sigusr1_handler(signum, frame):
             logger.fatal("Got fatal signal from worker processes, shutting "
                          "down. See stack trace above for root cause issue.")

vllm/v1/engine/output_processor.py

@@ -248,7 +248,7 @@ class OutputProcessor:
 
         ****************** NOTE FOR DEVELOPERS ******************
 
-        VLLM V1 minimizes the number of python loops over the full
+        vLLM V1 minimizes the number of python loops over the full
         batch to ensure system overheads are minimized. This is the 
         only function that should loop over EngineCoreOutputs.
 

vllm/v1/engine/processor.py

@@ -93,10 +93,10 @@ class Processor:
     ) -> None:
         # Best of not yet supported.
         if params.best_of is not None and params.best_of > 1:
-            raise ValueError("VLLM V1 does not yet support best_of.")
+            raise ValueError("vLLM V1 does not yet support best_of.")
         # Logits processors not supported.
         if params.logits_processors:
-            raise ValueError("VLLM V1 does not support per request "
+            raise ValueError("vLLM V1 does not support per request "
                              "user provided logits processors.")
 
     def _validate_params(