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

[Bugfix] Fix _CPU_MOE_ACT AssertionError when vLLM config not set (#32777)

Browse Source 
Signed-off-by: Karan Bansal <karanb192@gmail.com>
This commit is contained in:
Karan Bansal
2026-01-23 13:52:37 +05:30
committed by GitHub
parent 7ef5873752
commit fa6e599a61
2 changed files with 26 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/kernels/moe/test_cpu_fused_moe.py
View File

@@ -6,7 +6,7 @@ import torch
from tests.kernels.allclose_default import get_default_atol, get_default_rtol
from vllm._custom_ops import cpu_fused_moe, cpu_prepack_moe_weight
from vllm.model_executor.layers.fused_moe.cpu_fused_moe import _CPU_MOE_ACT
from vllm.model_executor.layers.fused_moe.cpu_fused_moe import _CPU_MOE_ACT_FN
from vllm.platforms import current_platform
from vllm.utils.torch_utils import set_random_seed
@@ -68,12 +68,7 @@ def ref_fused_moe(
tokens_for_this_expert, curr_w13, curr_w13_bias
)
# Note: to simulate the kernel implementation
gate_up = (
_CPU_MOE_ACT[activation]
.forward_native(gate_up)
.to(dtype=input.dtype)
.float()
)
gate_up = _CPU_MOE_ACT_FN[activation](gate_up).to(dtype=input.dtype).float()
expert_out = torch.nn.functional.linear(gate_up, curr_w2, curr_w2_bias)
outputs.append(expert_out)