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

Skip models that cannot currently init on Transformers v5 (#28471)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
(cherry picked from commit 51c599f0ec)
This commit is contained in:
Harry Mellor
2025-11-12 23:43:57 +00:00
committed by Kevin H. Luu
parent a035b5cffb
commit caf412e593
3 changed files with 6 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
.buildkite/test-pipeline.yaml
View File

@@ -868,12 +868,12 @@ steps:
optional: true
commands:
- pip install --upgrade git+https://github.com/huggingface/transformers
- pytest -v -s tests/models/test_initialization.py
- pytest -v -s tests/models/test_initialization.py -k 'not (Gemma3 or ModernBert or Qwen2_5_VL or Qwen2_5vl or Qwen2VL or TransformersMultiModalEmbeddingModel or TransformersMultiModalForSequenceClassification or Ultravox or Phi4Multimodal or LlavaNextVideo or MiniCPMO or Lfm2Moe or PaliGemma or RobertaForSequenceClassification or Ovis2_5 or Fuyu or DeepseekOCR or KimiVL)'
- pytest -v -s tests/models/test_transformers.py
- pytest -v -s tests/models/multimodal/processing/
- pytest -v -s tests/models/multimodal/test_mapping.py
# - pytest -v -s tests/models/multimodal/processing/
- pytest -v -s tests/models/multimodal/test_mapping.py -k 'not (Gemma3 or Qwen2VL or Qwen2_5_VL)'
- python3 examples/offline_inference/basic/chat.py
- python3 examples/offline_inference/vision_language.py --model-type qwen2_5_vl
# - python3 examples/offline_inference/vision_language.py --model-type qwen2_5_vl
# Whisper needs spawn method to avoid deadlock
- VLLM_WORKER_MULTIPROC_METHOD=spawn python3 examples/offline_inference/audio_language.py --model-type whisper