Skip to content

[xpu] refine fused_moe #4219

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 16, 2025
Merged

[xpu] refine fused_moe #4219

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions custom_ops/xpu_ops/src/ops/moe_layer.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -228,8 +228,9 @@ MoeLayer(const paddle::Tensor &x, const paddle::Tensor &gate_weight,
quant_method == "weight_only_int4") {
APPLY_MOE_LAYER_KERNEL(paddle::bfloat16, int4_t);
} else {
PD_THROW("MoeLayer not support x_type==%d, w_type==%d",
static_cast<int>(x_type), static_cast<int>(w_type));
PD_THROW("MoeLayer not support x_type=", static_cast<int>(x_type),
", w_type=", static_cast<int>(w_type),
", quant_method=", quant_method);
return {};
}
#undef APPLY_MOE_LAYER_KERNEL
Expand Down
7 changes: 1 addition & 6 deletions fastdeploy/model_executor/layers/backends/xpu/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,16 +16,11 @@
xpu backend methods
"""

from .moe.fused_moe import (
XPUMoEMethod,
XPUWeightOnlyMoeEpMethod,
XPUWeightOnlyMoEMethod,
)
from .moe.fused_moe import XPUMoEMethod, XPUWeightOnlyMoEMethod
from .quantization.weight_only import XPUWeightOnlyLinearMethod

__all__ = [
"XPUWeightOnlyLinearMethod",
"XPUMoEMethod",
"XPUWeightOnlyMoEMethod",
"XPUWeightOnlyMoeEpMethod",
]
Loading
Loading