YOLOV8+SAHI speed is a bit slow, how to improve speed?

[lhq15606085117]

Here is my code, which divides about 10 images and takes 15 seconds to complete the inference. Is there any way to improve the speed? Please reply, thank you!

yolov8_model_path = "best.pt"
download_yolov8s_model(yolov8_model_path)
detection_model = AutoDetectionModel.from_pretrained(
model_type='yolov8',
model_path=yolov8_model_path,
confidence_threshold=0.6,
device="cuda:0", # or 'cuda:0'
)

imgesData = "D:/ultralytics-main/ultralytics-main/save/12.jpg"
result = get_sliced_prediction(
imgesData,
detection_model,
slice_height=2880,
slice_width=2880,
overlap_height_ratio=0.1,
overlap_width_ratio=0.1,
postprocess_type="NMS",
postprocess_match_threshold=0.9,
postprocess_match_metric="IOS"
)