Skip to content

GitLab

Commit 241ea5cd authored by zhuwenwen's avatar zhuwenwen
Browse files

update fused_moe.py

parent 1faf662d
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
vllm/model_executor/layers/fused_moe/fused_moe.py
View file @ 241ea5cd
...@@ -1259,6 +1259,7 @@ def inplace_fused_experts( ...@@ -1259,6 +1259,7 @@ def inplace_fused_experts(
block_shape: Optional[List[int]] = None, #noqa: UP006 block_shape: Optional[List[int]] = None, #noqa: UP006
w1_bias: Optional[torch.Tensor] = None, w1_bias: Optional[torch.Tensor] = None,
w2_bias: Optional[torch.Tensor] = None, w2_bias: Optional[torch.Tensor] = None,
use_nn_moe: Optional[bool] = False,
) -> None: ) -> None:
fused_experts_impl(hidden_states, w1, w2, topk_weights, topk_ids, True, fused_experts_impl(hidden_states, w1, w2, topk_weights, topk_ids, True,
activation, apply_router_weight_on_input, use_fp8_w8a8, activation, apply_router_weight_on_input, use_fp8_w8a8,
...@@ -1293,6 +1294,7 @@ def inplace_fused_experts_fake( ...@@ -1293,6 +1294,7 @@ def inplace_fused_experts_fake(
block_shape: Optional[List[int]] = None, #noqa: UP006 block_shape: Optional[List[int]] = None, #noqa: UP006
w1_bias: Optional[torch.Tensor] = None, w1_bias: Optional[torch.Tensor] = None,
w2_bias: Optional[torch.Tensor] = None, w2_bias: Optional[torch.Tensor] = None,
use_nn_moe: Optional[bool] = False,
) -> None: ) -> None:
pass pass
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment