frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI Perf] Only test bfloat16 for tests/compile/test_fusion_all_reduce.py (#23132)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2025-08-19 22:18:52 -04:00
committed by GitHub
parent 0167efe20d
commit d46d417b58
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/compile/test_fusion_all_reduce.py
View File

@ -148,7 +148,7 @@ class TestAllReduceFusedAddRMSNormStaticQuantFP4Model(torch.nn.Module):
@pytest.mark.parametrize("batch_size", [8])
@pytest.mark.parametrize("seq_len", [8])
@pytest.mark.parametrize("hidden_size", [16])
@pytest.mark.parametrize("dtype", [torch.float16, torch.bfloat16])
@pytest.mark.parametrize("dtype", [torch.bfloat16])
@pytest.mark.skipif(envs.VLLM_TARGET_DEVICE not in ["cuda"],
reason="Only test on CUDA")
@pytest.mark.skipif(