feat(backends/python): use tempfile.gettempdir() instead of hardcoded /tmp (#9629)

Closes #9601

Makes the temporary scratch paths in vllm, vllm-omni, tinygrad, and pocket-tts
backends configurable via the standard TMPDIR env var, instead of always writing
to /tmp. This is a one-line change per call site that calls tempfile.gettempdir()
for the directory and keeps the same filename suffix.

Users who run on systems with a small root partition (or want to relocate scratch
files to a larger volume) can now redirect these by setting TMPDIR
(e.g. TMPDIR=/data/tmp), without affecting the existing LOCALAI_GENERATED_CONTENT_PATH
or LOCALAI_UPLOAD_PATH options that already cover other temp paths.

Files touched:
- backend/python/vllm/backend.py        (1 site: video base64 scratch)
- backend/python/tinygrad/backend.py    (1 site: image fallback dst)
- backend/python/pocket-tts/backend.py  (1 site: tts wav fallback dst)
- backend/python/vllm-omni/backend.py   (2 sites: video + audio scratch)

backend/python/pocket-tts/backend.py

@@ -8,6 +8,7 @@ import argparse
 import signal
 import sys
 import os
+import tempfile
 import traceback
 import scipy.io.wavfile
 import backend_pb2
@@ -204,7 +205,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             # Save audio to file
             output_path = request.dst
             if not output_path:
-                output_path = "/tmp/pocket-tts-output.wav"
+                output_path = os.path.join(tempfile.gettempdir(), "pocket-tts-output.wav")
 
             # Ensure output directory exists
             output_dir = os.path.dirname(output_path)

backend/python/tinygrad/backend.py

@@ -33,6 +33,7 @@ import json
 import os
 import signal
 import sys
+import tempfile
 import time
 from concurrent import futures
 from pathlib import Path
@@ -668,7 +669,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             )
             arr = img_tensor.numpy()
             image = Image.fromarray(arr)
-            dst = request.dst or "/tmp/tinygrad_image.png"
+            dst = request.dst or os.path.join(tempfile.gettempdir(), "tinygrad_image.png")
             image.save(dst)
             return backend_pb2.Result(success=True, message=dst)
         except Exception as exc:

backend/python/vllm-omni/backend.py

@@ -19,6 +19,7 @@ import base64
 import io
 import json
 import gc
+import tempfile
 
 from PIL import Image
 import torch
@@ -117,7 +118,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         # Try base64 decode
         try:
             timestamp = str(int(time.time() * 1000))
-            p = f"/tmp/vl-{timestamp}.data"
+            p = os.path.join(tempfile.gettempdir(), f"vl-{timestamp}.data")
             with open(p, "wb") as f:
                 f.write(base64.b64decode(video_path))
             video = VideoAsset(name=p).np_ndarrays
@@ -137,7 +138,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             audio_data = base64.b64decode(audio_path)
             # Save to temp file and load
             timestamp = str(int(time.time() * 1000))
-            p = f"/tmp/audio-{timestamp}.wav"
+            p = os.path.join(tempfile.gettempdir(), f"audio-{timestamp}.wav")
             with open(p, "wb") as f:
                 f.write(audio_data)
             audio_signal, sr = librosa.load(p, sr=16000)

backend/python/vllm/backend.py

@@ -10,6 +10,7 @@ import os
 import json
 import time
 import gc
+import tempfile
 from typing import List
 from PIL import Image
 
@@ -602,7 +603,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         """
         try:
             timestamp = str(int(time.time() * 1000))  # Generate timestamp
-            p = f"/tmp/vl-{timestamp}.data"  # Use timestamp in filename
+            p = os.path.join(tempfile.gettempdir(), f"vl-{timestamp}.data")
             with open(p, "wb") as f:
                 f.write(base64.b64decode(video_path))
             video = VideoAsset(name=p).np_ndarrays