xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-03 05:24:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI/Build][AMD] Skip test on test_hybrid_attention_mamba_tensor_shapes on ROCm, requires FLASHINFER (#29995)

Browse Source 
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
This commit is contained in:
rasmith 2025-12-04 03:30:22 -06:00 committed by GitHub
parent dfdda96747
commit f2f4cea6cc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tests/v1/worker/test_gpu_model_runner.py
View File

@ -761,6 +761,10 @@ def test_init_kv_cache_with_kv_sharing_valid():
assert kv_cache_config_after_init.kv_cache_groups[0].layer_names[1] == layer_1 assert kv_cache_config_after_init.kv_cache_groups[0].layer_names[1] == layer_1
@pytest.mark.skipif(
current_platform.is_rocm(),
reason="Attention backend FLASHINFER is not supported on ROCm.",
)
def test_hybrid_attention_mamba_tensor_shapes(monkeypatch): def test_hybrid_attention_mamba_tensor_shapes(monkeypatch):
""" """
The GPU model runner creates different views into the The GPU model runner creates different views into the