Refactor inference engine and task management: Remove obsolete inference engine and ONNX engine files, update inference processing to utilize batch handling, and enhance task management structure in documentation. Adjust paths for task specifications to align with new directory organization.

e2e/tests/test_performance.py

@@ -1,4 +1,5 @@
 import json
+import os
 import threading
 import time
 import uuid
@@ -6,6 +7,8 @@ from concurrent.futures import ThreadPoolExecutor
 
 import pytest
 
+_MEDIA = os.environ.get("MEDIA_DIR", "/media")
+
 
 def _percentile_ms(sorted_ms, p):
     n = len(sorted_ms)
@@ -122,14 +125,12 @@ def test_nft_perf_04_video_frame_rate_sse(
     warm_engine,
     http_client,
     jwt_token,
-    mock_loader_url,
     sse_client_factory,
 ):
     media_id = f"perf-sse-{uuid.uuid4().hex}"
-    base = mock_loader_url.rstrip("/")
     body = {
         "probability_threshold": 0.25,
-        "paths": [f"{base}/load/video_short01.mp4"],
+        "paths": [f"{_MEDIA}/video_short01.mp4"],
         "frame_period_recognition": 4,
         "frame_recognition_seconds": 2,
     }