lint and cleanup

vllm/model_executor/layers/moe.py

@@ -1,5 +1,3 @@
-from typing import Tuple
-
 import torch
 from torch import nn
 import torch.nn.functional as F
@@ -429,4 +427,4 @@ def fused_moe(hidden_states: torch.Tensor,
                          dim=1,
                          out=hidden_states)
     return torch.sum(intermediate_cache3.view(*intermediate_cache3.shape),
-                     dim=1)
+                     dim=1)

vllm/model_executor/models/mixtral.py

@@ -1,4 +1,3 @@
-
 # coding=utf-8
 # Adapted from
 # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py
@@ -272,7 +271,7 @@ def load_weights(self,
 
         expert_params_mapping = [
             # (param_name, weight_name, expert_id)
-            (f"ws" if weight_name in ["w1", "w3"] else "w2s",
+            ("ws" if weight_name in ["w1", "w3"] else "w2s",
              f"experts.{expert_id}.{weight_name}.weight", expert_id)
             for expert_id in range(self.config.num_local_experts)
             for weight_name in ["w1", "w2", "w3"]