feat: decouple dynamo sdk to support mutiple deployment targets (#905)

examples/sglang/components/worker.py

@@ -39,7 +39,6 @@ logger = logging.getLogger(__name__)
 
 @service(
     dynamo={
-        "enabled": True,
         "namespace": "dynamo",
     },
     resources={"gpu": 1},

examples/tensorrt_llm/components/frontend.py

@@ -48,7 +48,6 @@ class FrontendConfig(BaseModel):
 
 @service(
     dynamo={
-        "enabled": True,
         "namespace": "dynamo",
     },
     resources={"cpu": "10", "memory": "20Gi"},

examples/tensorrt_llm/components/kv_router.py

@@ -68,7 +68,6 @@ def parse_args(service_name, prefix) -> Namespace:
 
 @service(
     dynamo={
-        "enabled": True,
         "namespace": "dynamo",
     },
     resources={"cpu": "10", "memory": "20Gi"},

examples/tensorrt_llm/components/prefill_worker.py

@@ -28,7 +28,6 @@ logger = logging.getLogger(__name__)
 
 @service(
     dynamo={
-        "enabled": True,
         "namespace": "dynamo",
     },
     resources={"gpu": 1, "cpu": "10", "memory": "20Gi"},

examples/tensorrt_llm/components/processor.py

@@ -35,7 +35,6 @@ logger = logging.getLogger(__name__)
 
 @service(
     dynamo={
-        "enabled": True,
         "namespace": "dynamo",
     },
     resources={"cpu": "10", "memory": "20Gi"},

examples/tensorrt_llm/components/worker.py

@@ -29,7 +29,6 @@ logger = logging.getLogger(__name__)
 
 @service(
     dynamo={
-        "enabled": True,
         "namespace": "dynamo",
     },
     resources={"gpu": 1, "cpu": "10", "memory": "20Gi"},