xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 02:15:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update tests/kernels/moe/test_batched_moe.py

Browse Source 
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Signed-off-by: Fardin Hoque <kfhfar@amazon.com>
This commit is contained in:
Fardin Hoque 2025-10-17 10:11:52 -07:00 committed by GitHub
parent c2381fb05f
commit f46104deeb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/kernels/moe/test_batched_moe.py
View File

@ -95,7 +95,7 @@ class BatchedMMTensors:
@pytest.mark.parametrize("num_experts", [8, 32])
@pytest.mark.parametrize("max_tokens_per_expert", [32, 512])
@pytest.mark.parametrize("max_tokens_per_expert", [32, 224, 512])
@pytest.mark.parametrize("K", [128, 1024])
@pytest.mark.parametrize("N", [128, 1024])
@pytest.mark.parametrize("dtype", [torch.float8_e4m3fn, torch.bfloat16])