Skip to content

GitLab

Commit 39380c86 authored by zhuwenwen's avatar zhuwenwen
Browse files

remove redundant routed_scaling_factor

parent 6eb5b12c
Show whitespace changes
Inline Side-by-side
Showing with 0 additions and 2 deletions
vllm/model_executor/layers/quantization/awq_marlin.py
View file @ 39380c86
...@@ -532,7 +532,6 @@ class AWQMoEMethod(FusedMoEMethodBase): ...@@ -532,7 +532,6 @@ class AWQMoEMethod(FusedMoEMethodBase):
apply_router_weight_on_input: bool = False, apply_router_weight_on_input: bool = False,
activation: str = "silu", activation: str = "silu",
use_nn_moe: Optional[bool] = False, use_nn_moe: Optional[bool] = False,
routed_scaling_factor: Optional[float] = None,
use_fused_gate: Optional[bool] = False, use_fused_gate: Optional[bool] = False,
enable_eplb: bool = False, enable_eplb: bool = False,
expert_load_view: Optional[torch.Tensor] = None, expert_load_view: Optional[torch.Tensor] = None,
...@@ -557,7 +556,6 @@ class AWQMoEMethod(FusedMoEMethodBase): ...@@ -557,7 +556,6 @@ class AWQMoEMethod(FusedMoEMethodBase):
num_expert_group=num_expert_group, num_expert_group=num_expert_group,
custom_routing_function=custom_routing_function, custom_routing_function=custom_routing_function,
scoring_func=scoring_func, scoring_func=scoring_func,
routed_scaling_factor=routed_scaling_factor,
e_score_correction_bias=e_score_correction_bias, e_score_correction_bias=e_score_correction_bias,
indices_type=self.topk_indices_dtype, indices_type=self.topk_indices_dtype,
routed_scaling_factor=routed_scaling_factor, routed_scaling_factor=routed_scaling_factor,
......
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