Fix fastchat top_k (intel-analytics#10560)

* fix -1 top_k

* fix

* done

python/llm/src/ipex_llm/serving/fastchat/ipex_llm_worker.py

@@ -100,7 +100,9 @@ def generate_stream_gate(self, params):
         temperature = float(params.get("temperature", 1.0))
         repetition_penalty = float(params.get("repetition_penalty", 1.0))
         top_p = float(params.get("top_p", 1.0))
-        top_k = int(params.get("top_k", 0))  # 0 means disable
+        top_k = int(params.get("top_k", 1))
+        if top_k == -1:
+            top_k = 1
         max_new_tokens = int(params.get("max_new_tokens", 256))
         echo = bool(params.get("echo", True))
         stop_str = params.get("stop", None)