diff --git a/README.md b/README.md
index 7218f10b8..b21e677c4 100644
--- a/README.md
+++ b/README.md
@@ -351,6 +351,7 @@ python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port
 ```
 python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000 --mem-fraction-static 0.7
 ```
+- You can turn on [flashinfer](docs/flashinfer.md) to acclerate the inference by using highly optimized CUDA kernels.
 
 ### Supported Models
 - Llama
diff --git a/python/pyproject.toml b/python/pyproject.toml
index 6a133b54a..6fb94df40 100644
--- a/python/pyproject.toml
+++ b/python/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "sglang"
-version = "0.1.9"
+version = "0.1.10"
 description = "A structured generation langauge for LLMs." 
 readme = "README.md"
 requires-python = ">=3.8"
diff --git a/python/sglang/__init__.py b/python/sglang/__init__.py
index f0bd5ce75..2d01bcb03 100644
--- a/python/sglang/__init__.py
+++ b/python/sglang/__init__.py
@@ -1,4 +1,4 @@
-__version__ = "0.1.9"
+__version__ = "0.1.10"
 
 from sglang.api import *
 from sglang.global_config import global_config