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 4, 13:45 UTC
[CI][AMD][BugFix] Patch has_flashinfer decorator for test_select_rocm_aiter_backend (#41072)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
rasmith committed
Apr 28, 2026 at 21:12 UTC
856b15c62c8a574a1a0a289444d5b9a8120433e3
1 file changed
+1
-1
tests/kernels/moe/test_unquantized_backend_selection.py
+1
-1
@@ -85,7 +85,7 @@ def test_select_default_backend_by_platform(
85
86
87
@patch(
88
- "vllm.model_executor.layers.fused_moe.oracle.unquantized.has_flashinfer",
88
+ "vllm.utils.flashinfer.has_flashinfer",
89
return_value=False,
90
)
91
@patch(