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

[BUG] Fix async rlhf tests (#35811)

Browse Source 
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
This commit is contained in:
Aaron Hao
2026-03-11 15:06:10 -07:00
committed by GitHub
parent cf632499ee
commit d6b61e5166
2 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.buildkite/test_areas/distributed.yaml
View File

@@ -149,7 +149,7 @@ steps:
num_devices: 2
commands:
- pytest -v -s tests/distributed/test_context_parallel.py
# - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 examples/offline_inference/new_weight_syncing/rlhf_async_new_apis.py --- failing, need to re-enable
- VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 examples/offline_inference/new_weight_syncing/rlhf_async_new_apis.py
- VLLM_USE_DEEP_GEMM=1 VLLM_LOGGING_LEVEL=DEBUG python3 examples/offline_inference/data_parallel.py --model=Qwen/Qwen1.5-MoE-A2.7B -tp=1 -dp=2 --max-model-len=2048 --all2all-backend=deepep_high_throughput
- pytest -v -s tests/v1/distributed/test_dbo.py