biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Kernels] MoE refactor (#19636)

Browse Source 
Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Co-authored-by: ElizaWszola <ewszola@redhat.com>
This commit is contained in:
bnellnm
2025-07-02 09:08:27 -04:00
committed by GitHub
parent b95877509b
commit c1909e7e8c
36 changed files with 2698 additions and 1584 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/kernels/moe/test_nvfp4_moe.py
View File

@@ -14,7 +14,7 @@ from vllm.model_executor.layers.fused_moe.fused_moe import fused_topk
from vllm.platforms import current_platform
if not current_platform.has_device_capability(100):
pytest.skip(reason="Nvfp4 Requires compute capability of 10 or above.",
pytest.skip("Nvfp4 Requires compute capability of 10 or above.",
allow_module_level=True)
MNK_FACTORS = [