Reduce the image processing latency in VLM (#11541)

Co-authored-by: qiuxuan.lzw <qiuxuan.lzw@alibaba-inc.com>

python/sglang/srt/multimodal/processors/base_processor.py

@@ -313,7 +313,9 @@ class BaseMultimodalProcessor(ABC):
         try:
             if modality == Modality.IMAGE:
                 img, _ = load_image(data)
-                return img.convert("RGB") if discard_alpha_channel else img
+                if discard_alpha_channel and img.mode != "RGB":
+                    img = img.convert("RGB")
+                return img
             elif modality == Modality.VIDEO:
                 return load_video(data, frame_count_limit)
             elif modality == Modality.AUDIO: