[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/qwen3_next_mtp.py
+++ b/vllm/model_executor/models/qwen3_next_mtp.py
@@ -238,7 +238,8 @@ class Qwen3NextMTP(nn.Module, SupportsPP):
        self.lm_head = ParallelLMHead(self.unpadded_vocab_size,
                                      config.hidden_size,
                                      org_num_embeddings=config.vocab_size,
-                                      padding_size=DEFAULT_VOCAB_PADDING_SIZE)
+                                      padding_size=DEFAULT_VOCAB_PADDING_SIZE,
+                                      prefix=maybe_prefix(prefix, "lm_head"))
        self.logits_processor = LogitsProcessor(self.unpadded_vocab_size,
                                                config.vocab_size)
        self.make_empty_intermediate_tensors = (