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 13, 12:00 UTC
[BugFix] Fix Failing Ruff Check (#28469)
Signed-off-by: Jan van Lunteren <jvl@zurich.ibm.com>
jvlunteren committed
Nov 11, 2025 at 15:41 UTC
533b018f725fb9c2421e2c4b5a48d62fa5f1d844
1 file changed
+1
-1
tests/compile/test_fusions_e2e.py
+1
-1
@@ -74,7 +74,7 @@ if current_platform.is_cuda():
74
ModelBackendTestCase(
75
model_name="Qwen/Qwen3-30B-A3B",
76
model_kwargs=dict(max_model_len=1024),
77
- backend=_Backend.TRITON_ATTN,
77
+ backend=AttentionBackendEnum.TRITON_ATTN,
78
attention_fusions=0,
79
allreduce_fusions=97,
80
),