From aa49f148322a39727be110da51a6782d43a2f5d8 Mon Sep 17 00:00:00 2001 From: Dipika Sikka Date: Thu, 5 Jun 2025 14:21:53 -0400 Subject: [PATCH] [Quantization] Skip Fp4 Test for `compressed-tensors` (#19217) --- tests/quantization/test_compressed_tensors.py | 1 + 1 file changed, 1 insertion(+) diff --git a/tests/quantization/test_compressed_tensors.py b/tests/quantization/test_compressed_tensors.py index 807b24d4e3aa..03480343d4bd 100644 --- a/tests/quantization/test_compressed_tensors.py +++ b/tests/quantization/test_compressed_tensors.py @@ -651,6 +651,7 @@ def test_compressed_tensors_2of4_sparse_compressed(vllm_runner, args_2of4): assert output +@pytest.mark.skip(reason="Skip until the model config is updated") def test_compressed_tensors_nvfp4a16(vllm_runner): # run weight only example model = "nm-testing/TinyLlama-1.1B-Chat-v1.0-FP4"