Skip to content

GitLab

Commit 091cff41 authored by SAC_fanth's avatar SAC_fanth
Browse files

fp8增加fused_moe_gate参数

parent 9f68733a
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
vllm/model_executor/layers/quantization/fp8.py
View file @ 091cff41
...@@ -858,6 +858,7 @@ class Fp8MoEMethod(FusedMoEMethodBase): ...@@ -858,6 +858,7 @@ class Fp8MoEMethod(FusedMoEMethodBase):
e_score_correction_bias: Optional[torch.Tensor] = None, e_score_correction_bias: Optional[torch.Tensor] = None,
apply_router_weight_on_input: bool = False, apply_router_weight_on_input: bool = False,
activation: str = "silu", activation: str = "silu",
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,
logical_to_physical_map: Optional[torch.Tensor] = None, logical_to_physical_map: Optional[torch.Tensor] = None,
...@@ -886,6 +887,7 @@ class Fp8MoEMethod(FusedMoEMethodBase): ...@@ -886,6 +887,7 @@ class Fp8MoEMethod(FusedMoEMethodBase):
expert_load_view=expert_load_view, expert_load_view=expert_load_view,
logical_to_physical_map=logical_to_physical_map, logical_to_physical_map=logical_to_physical_map,
logical_replica_count=logical_replica_count, logical_replica_count=logical_replica_count,
use_fused_gate=use_fused_gate,
) )
if self.rocm_aiter_moe_enabled: if self.rocm_aiter_moe_enabled:
......
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