A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[CI/Build] Skip Qwen3-VL initialization tests until models are actually released (#25394)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Sep 23, 2025 at 04:18 UTC
f552d5e578077574276aa9d83139b91e1d5ae163
1 file changed
+5
-3
tests/models/registry.py
+5
-3
@@ -562,10 +562,12 @@ _MULTIMODAL_EXAMPLE_MODELS = {
562
"Qwen2_5OmniForConditionalGeneration": _HfExamplesInfo("Qwen/Qwen2.5-Omni-7B-AWQ"), # noqa: E501
563
"Qwen3VLForConditionalGeneration": _HfExamplesInfo("Qwen/Qwen3-VL-4B-Instruct", # noqa: E501
564
max_model_len=4096,
565
- min_transformers_version="4.57"), # noqa: E501
565
+ min_transformers_version="4.57",
566
+ is_available_online=False),
567
"Qwen3VLMoeForConditionalGeneration": _HfExamplesInfo("Qwen/Qwen3-VL-30B-A3B-Instruct", # noqa: E501
567
- max_model_len=4096,
568
- min_transformers_version="4.57"),
568
+ max_model_len=4096,
569
+ min_transformers_version="4.57",
570
+ is_available_online=False),
571
"RForConditionalGeneration": _HfExamplesInfo("YannQi/R-4B",
572
trust_remote_code=True),
573
"SkyworkR1VChatModel": _HfExamplesInfo("Skywork/Skywork-R1V-38B",