vlm: enforce pybase64 for image and str encode/decode (#10700)

test/srt/test_bnb.py

@@ -4,7 +4,6 @@ python3 -m unittest test_bnb.TestVisionModel.test_vlm
 python3 -m unittest test_bnb.TestLanguageModel.test_mmlu
 """
 
-import base64
 import io
 import json
 import multiprocessing as mp
@@ -15,6 +14,7 @@ from types import SimpleNamespace
 
 import numpy as np
 import openai
+import pybase64
 import requests
 from PIL import Image
 

test/srt/test_vision_chunked_prefill.py

@@ -3,7 +3,6 @@ Usage:
 python3 -m unittest test_vision_chunked_prefill.TestVisionChunkedPrefill.test_chunked_prefill
 """
 
-import base64
 import io
 import os
 import unittest
@@ -11,6 +10,7 @@ from concurrent.futures import ThreadPoolExecutor
 from typing import Union
 
 import numpy as np
+import pybase64
 import requests
 from PIL import Image
 
@@ -45,7 +45,7 @@ class TestVisionChunkedPrefill(CustomTestCase):
             pil_img = Image.fromarray(frame)
             buff = io.BytesIO()
             pil_img.save(buff, format="JPEG")
-            base64_str = base64.b64encode(buff.getvalue()).decode("utf-8")
+            base64_str = pybase64.b64encode(buff.getvalue()).decode("utf-8")
             base64_frames.append(base64_str)
 
         messages = [{"role": "user", "content": []}]

test/srt/test_vision_openai_server_common.py

@@ -1,10 +1,10 @@
-import base64
 import io
 import os
 from concurrent.futures import ThreadPoolExecutor
 
 import numpy as np
 import openai
+import pybase64
 import requests
 from PIL import Image
 
@@ -386,7 +386,7 @@ class ImageOpenAITestMixin(TestOpenAIMLLMServerBase):
             pil_img = Image.fromarray(frame)
             buff = io.BytesIO()
             pil_img.save(buff, format="JPEG")
-            base64_str = base64.b64encode(buff.getvalue()).decode("utf-8")
+            base64_str = pybase64.b64encode(buff.getvalue()).decode("utf-8")
             base64_frames.append(base64_str)
 
         messages = [{"role": "user", "content": []}]