fix: max tokens can only up to 2048 (#2734)

api/core/model_runtime/model_providers/xinference/llm/llm.py

@@ -308,6 +308,7 @@ class XinferenceAILargeLanguageModel(LargeLanguageModel):
                 type=ParameterType.INT,
                 use_template='max_tokens',
                 min=1,
+                max=credentials.get('context_length', 2048),
                 default=512,
                 label=I18nObject(
                     zh_Hans='最大生成长度',