20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[CI] Set max transformers version for Ultravox model test (#16149)

Browse Source 
Signed-off-by: Roger Wang <ywang@roblox.com>
This commit is contained in:
Roger Wang 2025-04-06 21:37:58 -07:00 committed by GitHub
parent fc0f87768a
commit bb8dab821e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tests/models/registry.py
View File

@ -329,7 +329,8 @@ _MULTIMODAL_EXAMPLE_MODELS = {
min_transformers_version="4.49"), # noqa: E501
"SkyworkR1VChatModel": _HfExamplesInfo("Skywork/Skywork-R1V-38B"),
"UltravoxModel": _HfExamplesInfo("fixie-ai/ultravox-v0_5-llama-3_2-1b", # noqa: E501
trust_remote_code=True),
trust_remote_code=True,
max_transformers_version="4.50"),
# [Encoder-decoder]
# Florence-2 uses BartFastTokenizer which can't be loaded from AutoTokenizer
# Therefore, we borrow the BartTokenizer from the original Bart model