[VLM] Initialize video input support for InternVL models (#18499)

Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
Isotr0py
2025-05-25 12:51:25 +08:00
committed by GitHub
parent 6ab681bcbe
commit 75f81750f3
10 changed files with 596 additions and 62 deletions

View File

@@ -258,6 +258,7 @@ def _test_processing_correctness_mistral(
"ibm-granite/granite-speech-3.3-8b",
"h2oai/h2ovl-mississippi-800m",
"OpenGVLab/InternVL2-1B",
"OpenGVLab/InternVL3-1B",
"HuggingFaceM4/Idefics3-8B-Llama3",
"HuggingFaceTB/SmolVLM2-2.2B-Instruct",
"moonshotai/Kimi-VL-A3B-Instruct",