diff --git a/docs/parameters.md b/docs/parameters.md
index 00d56ae6d..ab8361d2a 100644
--- a/docs/parameters.md
+++ b/docs/parameters.md
@@ -34,7 +34,7 @@ When using FastDeploy to deploy models (including offline inference and service
 | ```max_long_partial_prefills``` | `int` | When Chunked Prefill is enabled, maximum number of long requests in concurrent partial prefill batches, default: 1 |
 | ```long_prefill_token_threshold``` | `int` | When Chunked Prefill is enabled, requests with token count exceeding this value are considered long requests, default: max_model_len*0.04 |
 | ```static_decode_blocks``` | `int` | During inference, each request is forced to allocate corresponding number of blocks from Prefill's KVCache for Decode use, default: 2 |
-| ```reasoning_parser``` | `str` | Specify the reasoning parser to extract reasoning content from model output |
+| ```reasoning_parser``` | `str` | Specify the reasoning parser to extract reasoning content from model output, refer [reasoning output](features/reasoning_output.md) for more details |
 | ```use_cudagraph```                | `bool`      | Whether to use cuda graph, default False. It is recommended to read [graph_optimization.md](./features/graph_optimization.md) carefully before opening. Custom all-reduce needs to be enabled at the same time in multi-card scenarios. |
 | ```graph_optimization_config```    | `dict[str]`       | Can configure parameters related to calculation graph optimization, the default value is'{"use_cudagraph":false, "graph_opt_level":0, "cudagraph_capture_sizes": null }'，Detailed description reference [graph_optimization.md](./features/graph_optimization.md)|
 | ```enable_custom_all_reduce``` | `bool` | Enable Custom all-reduce, default: False |
diff --git a/docs/zh/parameters.md b/docs/zh/parameters.md
index ad395ee9a..7ed2ea4d5 100644
--- a/docs/zh/parameters.md
+++ b/docs/zh/parameters.md
@@ -32,7 +32,7 @@
 | ```max_long_partial_prefills```    | `int`       | 开启Chunked Prefill时，Prefill阶段并发中包启的最多长请求数，默认1 |
 | ```long_prefill_token_threshold``` | `int`       | 开启Chunked Prefill时，请求Token数超过此值的请求被视为长请求，默认为max_model_len*0.04 |
 | ```static_decode_blocks```         | `int`       | 推理过程中，每条请求强制从Prefill的KVCache分配对应块数给Decode使用，默认2|
-| ```reasoning_parser```             | `str`       | 指定要使用的推理解析器，以便从模型输出中提取推理内容 |
+| ```reasoning_parser```             | `str`       | 指定要使用的推理解析器，以便从模型输出中提取推理内容，详见[思考链内容](features/reasoning_output.md) |
 | ```use_cudagraph```                | `bool`      | 是否使用cuda graph，默认False。开启前建议仔细阅读  [graph_optimization.md](./features/graph_optimization.md)，在多卡场景需要同时开启 Custom all-reduce。 |
 | ```graph_optimization_config```    | `dict[str]`       | 可以配置计算图优化相关的参数，默认值为'{"use_cudagraph":false, "graph_opt_level":0, "cudagraph_capture_sizes": null }'，详细说明参考 [graph_optimization.md](./features/graph_optimization.md)|
 | ```enable_custom_all_reduce```     | `bool`      | 开启Custom all-reduce，默认False |
diff --git a/setup.py b/setup.py
index e13e70d07..c696ce7b6 100644
--- a/setup.py
+++ b/setup.py
@@ -181,7 +181,7 @@ def get_name():
 
 cmdclass_dict = {"bdist_wheel": CustomBdistWheel}
 cmdclass_dict["build_ext"] = CMakeBuild
-FASTDEPLOY_VERSION = os.environ.get("FASTDEPLOY_VERSION", "2.1.0")
+FASTDEPLOY_VERSION = os.environ.get("FASTDEPLOY_VERSION", "2.1.1")
 cmdclass_dict["build_optl"] = PostInstallCommand
 
 setup(