biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Model] Refactor Phi-4-multimodal to use merged processor and support V1 (#15477)

Browse Source 
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Isotr0py
2025-04-19 17:26:11 +08:00
committed by GitHub
parent d9737ca1c6
commit 83f3c3bd91
15 changed files with 818 additions and 1246 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/models/multimodal/processing/test_common.py
View File

@@ -274,6 +274,7 @@ def _test_processing_correctness_mistral(
"nvidia/NVLM-D-72B",
"google/paligemma-3b-mix-224",
"google/paligemma2-3b-ft-docci-448",
"microsoft/Phi-4-multimodal-instruct",
"mistralai/Pixtral-12B-2409",
"mistral-community/pixtral-12b",
"Qwen/Qwen-VL-Chat",