Fix qwen2-vl

vllm-project · Oct 29, 2024 · a41cff0 · a41cff0
1 parent 61c49b7
commit a41cff0
Showing 1 changed file with 6 additions and 2 deletions.
diff --git a/vllm/model_executor/models/qwen2_vl.py b/vllm/model_executor/models/qwen2_vl.py
@@ -938,15 +938,19 @@ def __init__(self,
             quant_config=None,
         )
 
-        self.model = Qwen2Model(config, cache_config, quant_config)
+        self.model = Qwen2Model(config,
+                                cache_config,
+                                quant_config,
+                                prefix="model")
 
         if get_pp_group().is_last_rank:
             if config.tie_word_embeddings:
                 self.lm_head = self.model.embed_tokens
             else:
                 self.lm_head = ParallelLMHead(config.vocab_size,
                                               config.hidden_size,
-                                              quant_config=quant_config)
+                                              quant_config=quant_config,
+                                              prefix="lm_head")
         else:
             self.lm_head = PPMissingLayer()