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 15, 02:15 UTC
[CI/Build] Add Transformers nightly tests in CI (#20924)
Signed-off-by: Isotr0py <2037008807@qq.com>
Isotr0py committed
Jul 15, 2025 at 00:33 UTC
6d0cf239c66936ff52582042698fd1aeb2a73bb6
1 file changed
+12
.buildkite/test-pipeline.yaml
+12
@@ -630,6 +630,18 @@ steps:
630
# e.g. pytest -v -s models/encoder_decoder/vision_language/test_mllama.py
631
# *To avoid merge conflicts, remember to REMOVE (not just comment out) them before merging the PR*
632
633
+- label: Transformers Nightly Models Test
634
+ working_dir: "/vllm-workspace/"
635
+ optional: true
636
+ commands:
637
+ - pip install --upgrade git+https://github.com/huggingface/transformers
638
+ - pytest -v -s models/test_initialization.py
639
+ - pytest -v -s tests/models/multimodal/processing/
640
+ - pytest -v -s tests/models/multimodal/test_mapping.py
641
+ - python3 examples/offline_inference/basic/chat.py
642
+ - python3 examples/offline_inference/audio_language.py --model-type whisper
643
+ - python3 examples/offline_inference/vision_language.py --model-type qwen2_5_vl
644
+
645
##### 1 GPU test #####
646
##### multi gpus test #####
647