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 5, 23:30 UTC
[ROCm][CI] Fix wvSplitKrc mock argument order in test_rocm_unquantized_gemm (#38167)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Andreas Karatzas committed
Mar 26, 2026 at 06:54 UTC
37a83007fef9925609a8d9b7c7b86bb41dab4e5d
1 file changed
+1
-1
tests/model_executor/layers/test_rocm_unquantized_gemm.py
+1
-1
@@ -76,7 +76,7 @@ def test_rocm_unquantized_gemm_gfx950_wvsplitkrc_path(monkeypatch):
76
monkeypatch.setattr("vllm.platforms.rocm.on_gfx950", lambda: True)
77
monkeypatch.setattr(utils, "num_compute_units", lambda: 120)
78
79
- wvsplitkrc_mock = MagicMock(side_effect=lambda w, x_view, _, __: x_view @ w.t())
79
+ wvsplitkrc_mock = MagicMock(side_effect=lambda x_view, w, _, __: x_view @ w.t())
80
monkeypatch.setattr(utils.ops, "wvSplitKrc", wvsplitkrc_mock)
81
wvsplitk_mock = MagicMock(side_effect=lambda w, x_view, _, __: x_view @ w.t())
82
monkeypatch.setattr(utils.ops, "wvSplitK", wvsplitk_mock)