diff --git a/vllm/server.py b/vllm/server.py
index d51da13..36dbd03 100644
--- a/vllm/server.py
+++ b/vllm/server.py
@@ -36,7 +36,7 @@ class CompletionRequest(BaseModel):
     """OpenAI-compatible completion request"""
     model: str = Field(default="qwen-2.5-7b")
     prompt: str | List[str] = Field(..., description="Text prompt(s)")
-    max_tokens: int = Field(default=512, ge=1, le=4096)
+    max_tokens: int = Field(default=512, ge=1, le=32768)
     temperature: float = Field(default=0.7, ge=0.0, le=2.0)
     top_p: float = Field(default=1.0, ge=0.0, le=1.0)
     n: int = Field(default=1, ge=1, le=10)
@@ -54,7 +54,7 @@ class ChatCompletionRequest(BaseModel):
     """OpenAI-compatible chat completion request"""
     model: str = Field(default="qwen-2.5-7b")
     messages: List[ChatMessage] = Field(..., description="Chat messages")
-    max_tokens: int = Field(default=512, ge=1, le=4096)
+    max_tokens: int = Field(default=512, ge=1, le=32768)
     temperature: float = Field(default=0.7, ge=0.0, le=2.0)
     top_p: float = Field(default=1.0, ge=0.0, le=1.0)
     n: int = Field(default=1, ge=1, le=10)