[VLM] merged multimodal processor and V1 support for idefics3 (#12660)

Signed-off-by: Isotr0py <2037008807@qq.com> Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-02-04 20:00:51 +08:00
parent 18a88fcccc
commit 815079de8e
7 changed files with 320 additions and 462 deletions
--- a/tests/models/multimodal/processing/test_common.py
+++ b/tests/models/multimodal/processing/test_common.py
@@ -149,6 +149,7 @@ def _test_processing_correctness(
    "adept/fuyu-8b",
    "h2oai/h2ovl-mississippi-800m",
    "OpenGVLab/InternVL2-1B",
+    "HuggingFaceM4/Idefics3-8B-Llama3",
    "llava-hf/llava-1.5-7b-hf",
    "llava-hf/llava-v1.6-mistral-7b-hf",
    "llava-hf/LLaVA-NeXT-Video-7B-hf",