fix(vram): improve VRAM checking logic

- Update VRAM checking logic in app.py and model_utils.py
- Add None and type checks for VRAM values
- Adjust concurrency limit calculation in app.py
- Modify clean_vram function to handle cases with no VRAM information

magic_pdf/model/sub_modules/model_utils.py

@@ -43,7 +43,7 @@ def get_res_list_from_layout_res(layout_res):
 
 def clean_vram(device, vram_threshold=8):
     total_memory = get_vram(device)
-    if total_memory <= vram_threshold:
+    if total_memory and total_memory <= vram_threshold:
         gc_start = time.time()
         clean_memory()
         gc_time = round(time.time() - gc_start, 2)
@@ -54,4 +54,4 @@ def get_vram(device):
     if torch.cuda.is_available() and device != 'cpu':
         total_memory = torch.cuda.get_device_properties(device).total_memory / (1024 ** 3)  # 将字节转换为 GB
         return total_memory
-    return 0
+    return None

projects/gradio_app/app.py

@@ -187,8 +187,9 @@ def to_pdf(file_path):
 
 def get_concurrency_limit(vram_threshold=7.5):
     vram = get_vram(device = get_device())
-    concurrency_limit = int(vram // vram_threshold)
-    if concurrency_limit < 1:
+    if vram is not None and isinstance(vram, (int, float)):
+        concurrency_limit = max(1, int(vram // vram_threshold))
+    else:
         concurrency_limit = 1
     # logger.info(f'concurrency_limit: {concurrency_limit}')
     return concurrency_limit