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 7, 19:00 UTC
[CI] Fix Distributed Tests (#35236)
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Robert Shaw committed
Feb 24, 2026 at 17:31 UTC
ea97750414844743afb677c33eb4af2c9e34dc8d
1 file changed
+1
-1
.buildkite/test_areas/distributed.yaml
+1
-1
@@ -145,7 +145,7 @@ steps:
145
num_devices: 2
146
commands:
147
- pytest -v -s tests/distributed/test_context_parallel.py
148
- - cd examples/offline_inference/new_weight_syncing && VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 rlhf_async_new_apis.py
148
+ - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 examples/offline_inference/new_weight_syncing/rlhf_async_new_apis.py
149
- 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
150
- pytest -v -s tests/v1/distributed/test_dbo.py
151