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, 01:15 UTC
[CI/Build] Try to make beam search test less flaky (#34885)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Feb 19, 2026 at 19:16 UTC
23210a911eb9c8bfb627d96481244ac4360877b3
1 file changed
+1
-1
tests/samplers/test_beam_search.py
+1
-1
@@ -27,7 +27,7 @@ EXTRA_ENGINE_KWARGS: dict = (
27
max_num_seqs=1,
28
)
29
if current_platform.is_rocm()
30
- else {}
30
+ else dict(async_scheduling=False, max_num_seqs=1)
31
)
32
33
# FIXME(zhuohan): The test can not pass if we: