[Bug] Fix vLLM config is not set error (#29999)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
@@ -460,6 +460,7 @@ def cutlass_moe_fp8(
|
||||
expert_map: torch.Tensor | None = None,
|
||||
apply_router_weight_on_input: bool = False,
|
||||
global_num_experts: int = -1,
|
||||
parallel_config=None,
|
||||
) -> torch.Tensor:
|
||||
"""
|
||||
This function computes a a8w8-quantized Mixture of Experts (MoE) layer
|
||||
@@ -537,6 +538,7 @@ def cutlass_moe_fp8(
|
||||
c_strides2=c_strides2,
|
||||
quant_config=quant_config,
|
||||
),
|
||||
parallel_config=parallel_config,
|
||||
)
|
||||
|
||||
return fn(
|
||||
|
||||
Reference in New Issue
Block a user