diff --git a/python/sglang/srt/models/llama.py b/python/sglang/srt/models/llama.py
index 71b4ed1b7..0cf0b344e 100644
--- a/python/sglang/srt/models/llama.py
+++ b/python/sglang/srt/models/llama.py
@@ -325,8 +325,8 @@ class LlamaForCausalLM(nn.Module):
         self.config = config
         self.quant_config = quant_config
         self.model = LlamaModel(config, quant_config=quant_config)
-        # Llama 3.2 1B Insturct set tie_word_embeddings to True
-        # Llama 3.1 8B Insturct set tie_word_embeddings to False
+        # Llama 3.2 1B Instruct set tie_word_embeddings to True
+        # Llama 3.1 8B Instruct set tie_word_embeddings to False
         if self.config.tie_word_embeddings:
             self.lm_head = self.model.embed_tokens
         else: