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 6, 10:45 UTC
[CI] Fix wrong path test file, missing `rlhf_async_new_apis.py` (#37532)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
TJian committed
Mar 19, 2026 at 17:21 UTC
da70c87e81a84138ea1f745e116bdaa41ec0180e
1 file changed
+1
-1
.buildkite/test_areas/distributed.yaml
+1
-1
@@ -194,7 +194,7 @@ steps:
194
num_devices: 2
195
commands:
196
- pytest -v -s tests/distributed/test_context_parallel.py
197
- - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 examples/offline_inference/new_weight_syncing/rlhf_async_new_apis.py
197
+ - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 examples/rl/rlhf_async_new_apis.py
198
- 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
199
- pytest -v -s tests/v1/distributed/test_dbo.py
200