[claudesquad] update from 'add-llama-1' on 10 Jan 26 21:03 CST

nanovllm/models/qwen3.py

@@ -9,6 +9,7 @@ from nanovllm.layers.layernorm import RMSNorm
 from nanovllm.layers.linear import QKVParallelLinear, MergedColumnParallelLinear, RowParallelLinear
 from nanovllm.layers.rotary_embedding import get_rope
 from nanovllm.layers.embed_head import VocabParallelEmbedding, ParallelLMHead
+from nanovllm.models.registry import register_model
 
 
 class Qwen3Attention(nn.Module):
@@ -186,6 +187,7 @@ class Qwen3Model(nn.Module):
         return hidden_states
 
 
+@register_model("Qwen3ForCausalLM", "Qwen2ForCausalLM")
 class Qwen3ForCausalLM(nn.Module):
     packed_modules_mapping = {
         "q_proj": ("qkv_proj", "q"),