From 4f4f8eaa78fb861dcb0b141951f7496b47ea679e Mon Sep 17 00:00:00 2001 From: Micah Williamson Date: Tue, 14 Apr 2026 11:14:31 -0500 Subject: [PATCH] [ROCm][CI] Fix condition for `test_per_token_group_quant_fp8_packed` (#39730) Signed-off-by: Micah Williamson --- tests/kernels/quantization/test_per_token_group_quant.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tests/kernels/quantization/test_per_token_group_quant.py b/tests/kernels/quantization/test_per_token_group_quant.py index f2edd92765..5447a43ffb 100644 --- a/tests/kernels/quantization/test_per_token_group_quant.py +++ b/tests/kernels/quantization/test_per_token_group_quant.py @@ -6,6 +6,7 @@ import pytest import torch from vllm.model_executor.layers.quantization.utils import fp8_utils, int8_utils +from vllm.platforms import current_platform @pytest.mark.parametrize( @@ -80,7 +81,9 @@ def test_per_token_group_quant_fp8( ], ) @pytest.mark.parametrize("poisoned_scales", [False, True]) -@pytest.mark.skipif(not torch.cuda.is_available(), reason="CUDA not available") +@pytest.mark.skipif( + not current_platform.is_cuda(), reason="DeepGEMM not available on this platform" +) def test_per_token_group_quant_fp8_packed( num_tokens, hidden_dim, group_size, poisoned_scales ):