Higher priority for user input of max_prefill_tokens & format (#540)

python/sglang/lang/interpreter.py

@@ -507,7 +507,7 @@ class StreamExecutor:
                     )
                     return
 
-                else: # Speculative execution on models with completion interface
+                else:  # Speculative execution on models with completion interface
                     comp, meta_info = self._spec_gen(sampling_params)
 
             self.text_ += comp

python/sglang/lang/ir.py

@@ -81,12 +81,10 @@ class SglSamplingParams:
             "top_p": self.top_p,
             "top_k": self.top_k,
         }
-        
+
     def to_litellm_kwargs(self):
         if self.regex is not None:
-            warnings.warn(
-                "Regular expression is not supported in the LiteLLM backend."
-            )
+            warnings.warn("Regular expression is not supported in the LiteLLM backend.")
         return {
             "max_tokens": self.max_new_tokens,
             "stop": self.stop or None,