[Model] Pass param prefix to LLMHead (#24862)

Signed-off-by: whx-sjtu <2952154980@qq.com>
2025-09-17 16:01:27 +08:00
parent 03191cd8f0
commit 4a9375fe9d
58 changed files with 102 additions and 31 deletions
--- a/vllm/model_executor/models/qwen2_moe.py
+++ b/vllm/model_executor/models/qwen2_moe.py
@@ -519,7 +519,8 @@ class Qwen2MoeForCausalLM(nn.Module, SupportsPP, SupportsLoRA):
                                   prefix=maybe_prefix(prefix, "model"))
        self.lm_head = ParallelLMHead(config.vocab_size,
                                      config.hidden_size,
-                                      quant_config=quant_config)
+                                      quant_config=quant_config,
+                                      prefix=maybe_prefix(prefix, "lm_head"))
        if self.config.tie_word_embeddings:
            self.lm_head.weight = self.model.embed_tokens.weight
        self.logits_processor = LogitsProcessor(config.vocab_size)