obscura/vllm
2
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2026-06-06 00:16:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

[XPU] skip unapplied UT in test_gpu_model_runner.py (#44289)

Browse Source 
Signed-off-by: Yan Ma <yan.ma@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Yan Ma
2026-06-04 08:48:17 +08:00
committed by GitHub
parent 128adabfe0
commit 0414d75410
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/v1/worker/test_gpu_model_runner.py
+4 -4
View File
@@ -1072,8 +1072,8 @@ def test_init_kv_cache_with_kv_sharing_valid(default_vllm_config):
@pytest.mark.skipif(
current_platform.is_rocm(),
reason="Attention backend FLASHINFER is not supported on ROCm.",
not current_platform.is_cuda(),
reason="Attention backend FLASHINFER is only supported on CUDA.",
)
def test_hybrid_attention_mamba_tensor_shapes():
"""
@@ -1508,8 +1508,8 @@ def test_is_uniform_decode() -> None:
@pytest.mark.skipif(
current_platform.is_rocm(),
reason="Attention backend FLASHINFER is not supported on ROCm.",
not current_platform.is_cuda(),
reason="Attention backend FLASHINFER is only supported on CUDA.",
)
def test_mamba_cache_raises_when_max_num_seqs_exceeds_blocks():
"""Test that a ValueError is raised when max_num_seqs exceeds the