@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 4a1550d22d

Fork 0

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 8, 12:30 UTC

[ROCm][CI] Fix test_sequence_parallel.py location in AMD CI pipeline (#34280)

Signed-off-by: Micah Williamson <micah.williamson@amd.com>

Micah Williamson committed Feb 10, 2026 at 19:08 UTC 4a1550d22d7058e129d0e1257e726b3bf4a77025

1 file changed +1 -1

.buildkite/test-amd.yaml

+1 -1

@@ -1334,7 +1334,7 @@ steps:

1334 - pytest -v -s ./compile/test_wrapper.py

1335 - VLLM_TEST_SAME_HOST=1 torchrun --nproc-per-node=4 distributed/test_same_node.py | grep 'Same node test passed'

1336 - VLLM_TEST_SAME_HOST=1 VLLM_TEST_WITH_DEFAULT_DEVICE_SET=1 torchrun --nproc-per-node=4 distributed/test_same_node.py | grep 'Same node test passed'

1337 - - pytest -v -s distributed/test_sequence_parallel.py

1337 + - pytest -v -s compile/correctness_e2e/test_sequence_parallel.py

1338 - CUDA_VISIBLE_DEVICES=0,1 pytest -v -s v1/shutdown

1339 - pytest -v -s v1/worker/test_worker_memory_snapshot.py

1340