xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-22 23:05:43 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix][CI] Fix Distributed Tests (4 GPUs) async_sched+ray test (#27195)

Browse Source 
Signed-off-by: NickLucche <nlucches@redhat.com>
This commit is contained in:
Nicolò Lucchesi 2025-10-20 18:34:54 +02:00 committed by GitHub
parent 4d0f266113
commit f9e7ad5400
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tests/v1/distributed/test_async_llm_dp.py
View File

@ -78,6 +78,9 @@ async def generate(
async def test_load( async def test_load(
output_kind: RequestOutputKind, data_parallel_backend: str, async_scheduling: bool output_kind: RequestOutputKind, data_parallel_backend: str, async_scheduling: bool
): ):
if async_scheduling and data_parallel_backend == "ray":
# TODO(NickLucche) Re-enable when async scheduling is supported
pytest.skip("Async scheduling is not supported with ray")
stats_loggers = {} stats_loggers = {}
@dataclass @dataclass