[Feat] Add modalities for vision server when handling pixel values for llava (#1346)

2024-09-09 02:07:34 -07:00
parent 8e6bdf851c
commit 662ecd9368
11 changed files with 40 additions and 2 deletions
@@ -130,6 +130,7 @@ class Req:
        self.image_sizes = None
        self.image_offsets = None
        self.pad_value = None
+        self.modalities = None

        # Prefix info
        self.extend_input_len = 0