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] fix test_rotary_embedding_opcheck format error (#41202)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Chauncey committed
Apr 29, 2026 at 15:32 UTC
92879e12ba130e12bcc2728939eba86b2644122f
1 file changed
+1
-3
tests/kernels/core/test_rotary_embedding.py
+1
-3
@@ -35,9 +35,7 @@ def rotary_embedding_opcheck(
35
@pytest.mark.parametrize("seq_len", [11, 1024])
36
@pytest.mark.parametrize("use_key", [True, False])
37
@pytest.mark.parametrize("head_stride_is_contiguous", [True, False])
38
-@pytest.mark.parametrize(
39
- "dtype", [torch.float32, torch.bfloat16]
40
-)
38
+@pytest.mark.parametrize("dtype", [torch.float32, torch.bfloat16])
39
def test_rotary_embedding_opcheck(
40
default_vllm_config,
41
dist_init,