update the modal deployment logic

.gitea/workflows/test_trigger_modal_triton.yaml

@@ -7,7 +7,7 @@ jobs:
   deploy-to-modal:
     runs-on:  ubuntu-latest
     container:
-      image: gitea-modal-runner:latest 
+      image: gitea-modal-runner:latest  # where build the code
     
     steps:
       - name: Checkout code

workspace/sprint_1_2/CODEBASE/infra/implementation/triton_run/modal_triton.py

@@ -25,6 +25,26 @@ triton_image = (
 )
 
 app = modal.App("triton-s3-service", image=triton_image)
+
+# -------------------------------------------------------------
+# THE UNIFIED SERVICE FUNCTION (1 Container, 1 GPU, 1 Triton Process)
+# -------------------------------------------------------------
+
+@app.function(
+    gpu="T4", # for the expense
+    timeout=3600,
+    max_containers=3, # Strict production capping
+    min_containers=1, # for keeping warm and prevention,
+    buffer_containers=2, # Number of additional idle containers to maintain under active load.
+    scaledown_window=30, # Max time (in seconds) a container can remain idle while scaling down.
+    volumes= {
+        '/mnt/vkist-ml-model' : modal.CloudBucketMount(bucket_name="vkist-ml-model", secret=modal.Secret.from_name("aws-secrets"))
+    },
+    secrets=[modal.Secret.from_name("aws-secrets")]
+)
+@modal.asgi_app()
+def unified_triton_server():
+
     from fastapi import FastAPI, Response, Request,HTTPException
     from fastapi.responses import StreamingResponse # 👈 ADD THIS IMPORT
     import httpx
@@ -194,24 +214,6 @@ async def forward_list_models():
             r = await client.get("http://127.0.0.1:8000/v2/models")
             return Response(content=r.content, status_code=r.status_code, media_type=r.headers.get("content-type"))
 
-# -------------------------------------------------------------
-# THE UNIFIED SERVICE FUNCTION (1 Container, 1 GPU, 1 Triton Process)
-# -------------------------------------------------------------
-
-@app.function(
-    gpu="T4", # for the expense
-    timeout=3600,
-    max_containers=3, # Strict production capping
-    min_containers=1, # for keeping warm and prevention,
-    buffer_containers=2, # Number of additional idle containers to maintain under active load.
-    scaledown_window=30, # Max time (in seconds) a container can remain idle while scaling down.
-    volumes= {
-        '/mnt/vkist-ml-model' : modal.CloudBucketMount(bucket_name="vkist-ml-model", secret=modal.Secret.from_name("aws-secrets"))
-    },
-    secrets=[modal.Secret.from_name("aws-secrets")]
-)
-@modal.asgi_app()
-def unified_triton_server():
     print("🚀 Booting ONE Triton Instance inside ONE A100 Container...")
     
     # Spawns Triton in the background. It will automatically read