diff --git a/vllm/model_executor/models/llama_eagle3.py b/vllm/model_executor/models/llama_eagle3.py index 2d859bd491..549e8b7bf6 100644 --- a/vllm/model_executor/models/llama_eagle3.py +++ b/vllm/model_executor/models/llama_eagle3.py @@ -60,7 +60,7 @@ class LlamaDecoderLayer(LlamaDecoderLayer): self.self_attn.total_num_kv_heads, bias=qkv_bias, quant_config=quant_config, - prefix=maybe_prefix(prefix, "qkv_proj"), + prefix=maybe_prefix(prefix, "self_attn.qkv_proj"), ) self.hidden_norm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)