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

[CI]Add transformers_utils to Async Engine, Inputs, Utils, Worker Test (#24615)

Browse Source 
Signed-off-by: Xingyu Liu <charlotteliu12x@gmail.com>
This commit is contained in:
Xingyu Liu
2025-09-11 01:52:10 -07:00
committed by GitHub
parent d14c4ebf08
commit 0fc36463e0
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.buildkite/test-pipeline.yaml
View File

@ -54,6 +54,7 @@ steps:
- tests/utils_
- tests/worker
- tests/standalone_tests/lazy_imports.py
- tests/transformers_utils
commands:
- python3 standalone_tests/lazy_imports.py
- pytest -v -s mq_llm_engine # MQLLMEngine
@ -63,6 +64,7 @@ steps:
- pytest -v -s multimodal
- pytest -v -s utils_ # Utils
- pytest -v -s worker # Worker
- pytest -v -s transformers_utils # transformers_utils
- label: Python-only Installation Test # 10min
timeout_in_minutes: 20
@ -822,8 +824,8 @@ steps:
# Avoid importing model tests that cause CUDA reinitialization error
- pytest models/test_transformers.py -v -s -m 'distributed(num_gpus=2)'
- pytest models/language -v -s -m 'distributed(num_gpus=2)'
- pytest models/multimodal -v -s -m 'distributed(num_gpus=2)' --ignore models/multimodal/generation/test_whisper.py
- VLLM_WORKER_MULTIPROC_METHOD=spawn pytest models/multimodal/generation/test_whisper.py -v -s -m 'distributed(num_gpus=2)'
- pytest models/multimodal -v -s -m 'distributed(num_gpus=2)' --ignore models/multimodal/generation/test_whisper.py
- VLLM_WORKER_MULTIPROC_METHOD=spawn pytest models/multimodal/generation/test_whisper.py -v -s -m 'distributed(num_gpus=2)'
# test sequence parallel
- pytest -v -s distributed/test_sequence_parallel.py
# this test fails consistently.