[V1] AsyncLLM Implementation (#9826)

Signed-off-by: Nick Hill <nickhill@us.ibm.com>
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

vllm/entrypoints/llm.py

@@ -210,8 +210,11 @@ class LLM:
         # Logic to switch between engines is done at runtime instead of import
         # to avoid import order issues
         self.engine_class = self.get_engine_class()
+
+        # TODO(rob): enable mp by default (issue with fork vs spawn)
         self.llm_engine = self.engine_class.from_engine_args(
             engine_args, usage_context=UsageContext.LLM_CLASS)
+
         self.request_counter = Counter()
 
     @staticmethod