Upgrade to vllm 0.17.0 corex v4.1 overlay

vllm/model_executor/models/teleflm.py

@@ -27,6 +27,7 @@ import torch
 import torch.nn as nn
 
 from vllm.config import VllmConfig
+from vllm.distributed import get_pp_group
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
 from vllm.model_executor.models.llama import (
     LlamaDecoderLayer,
@@ -69,7 +70,7 @@ class TeleFLMForCausalLM(LlamaForCausalLM):
         super().__init__(vllm_config=vllm_config, prefix=prefix)
         # mup
         self.use_mup = self.config.use_mup
-        if self.use_mup:
+        if self.use_mup and get_pp_group().is_last_rank:
             self.mup_scale_factor = self.config.mup_scale_factor
             self.output_mult = self.config.output_mult / self.mup_scale_factor
             logit_scale = self.output_mult