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, 09:30 UTC
[CI] Removing deprecated rlhf examples reference (#37585)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Andreas Karatzas committed
Mar 20, 2026 at 02:20 UTC
bd8c4c0752b7542c687ed06c2284cfb594a61e48
2 files changed
-3
.buildkite/test-amd.yaml
-2
@@ -1511,8 +1511,6 @@ steps:
1511
- vllm/distributed/
1512
- tests/distributed/test_torchrun_example.py
1513
- tests/distributed/test_torchrun_example_moe.py
1514
- - examples/offline_inference/rlhf.py
1515
- - examples/offline_inference/rlhf_colocate.py
1514
- examples/rl/
1515
- tests/examples/offline_inference/data_parallel.py
1516
- vllm/platforms/rocm.py
.buildkite/test_areas/distributed.yaml
-1
@@ -88,7 +88,6 @@ steps:
88
- vllm/distributed/
89
- tests/distributed/test_torchrun_example.py
90
- tests/distributed/test_torchrun_example_moe.py
91
- - examples/offline_inference/rlhf.py
91
- examples/offline_inference/rlhf_colocate.py
92
- examples/rl/
93
- tests/examples/offline_inference/data_parallel.py