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

@@ -25,16 +25,36 @@ triton_image = (
 )
 
 app = modal.App("triton-s3-service", image=triton_image)
-from fastapi import FastAPI, Response, Request,HTTPException
-from fastapi.responses import StreamingResponse # 👈 ADD THIS IMPORT
-import httpx
-web_app = FastAPI()
+
 # -------------------------------------------------------------
-# FASTAPI PROXY ROUTING (Living inside the container)
+# THE UNIFIED SERVICE FUNCTION (1 Container, 1 GPU, 1 Triton Process)
 # -------------------------------------------------------------
 
-@web_app.get("/v2/health/ready")
-async def forward_health():
+@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
+    web_app = FastAPI()
+    # -------------------------------------------------------------
+    # FASTAPI PROXY ROUTING (Living inside the container)
+    # -------------------------------------------------------------
+
+    @web_app.get("/v2/health/ready")
+    async def forward_health():
         """Proxies external HTTP REST calls straight to Triton's internal inference engine"""
         async with httpx.AsyncClient() as client:
             try:
@@ -43,9 +63,9 @@ async def forward_health():
             except Exception as e:
                 return Response(content=f"Triton booting models from S3... Error: {str(e)}", status_code=503)
 
-@web_app.get("/metrics")
-@web_app.get("/")
-async def forward_metrics():
+    @web_app.get("/metrics")
+    @web_app.get("/")
+    async def forward_metrics():
         """Proxies external metric calls straight to Triton's internal metrics engine"""
         async with httpx.AsyncClient() as client:
             try:
@@ -54,9 +74,9 @@ async def forward_metrics():
             except Exception as e:
                 return Response(content=f"Waiting for metrics channel... Error: {str(e)}", status_code=503)
 
-# 👇 ADD THIS CATCH-ALL ROUTE HERE 👇
-@web_app.api_route("/v2/{path:path}", methods=["GET", "POST"])
-async def proxy_all_triton_request(path: str, request: Request):
+    # 👇 ADD THIS CATCH-ALL ROUTE HERE 👇
+    @web_app.api_route("/v2/{path:path}", methods=["GET", "POST"])
+    async def proxy_all_triton_request(path: str, request: Request):
         import tritonclient.grpc.aio as grpcclient 
         from tritonclient.grpc import service_pb2, service_pb2_grpc
         from tritonclient.grpc import _utils as grpc_utils #InferenceServerClient 
@@ -188,30 +208,12 @@ async def proxy_all_triton_request(path: str, request: Request):
                     status_code=502
                 )
 
-@web_app.get("/v2/models")
-async def forward_list_models():
+    @web_app.get("/v2/models")
+    async def forward_list_models():
         async with httpx.AsyncClient() as client:
             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