diff --git a/3rdparty/flashinfer b/3rdparty/flashinfer
new file mode 160000
index 00000000000..00cf5f46fdb
--- /dev/null
+++ b/3rdparty/flashinfer
@@ -0,0 +1 @@
+Subproject commit 00cf5f46fdbb4f1dbd9277fe3b842621c1d9e7dc
diff --git a/README.md b/README.md
index fc666595d14..40fe5d5c357 100644
--- a/README.md
+++ b/README.md
@@ -164,4 +164,4 @@ python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port
 }
 ```
 
-We learned from the design and reused some code of the following projects: [Guidance](https://github.com/guidance-ai/guidance), [vLLM](https://github.com/vllm-project/vllm), [LightLLM](https://github.com/ModelTC/lightllm), [FlashInfer](https://github.com/flashinfer-ai/flashinfer), [LMQL](https://github.com/eth-sri/lmql).
+We learned from the design and reused some code of the following projects: [Guidance](https://github.com/guidance-ai/guidance), [vLLM](https://github.com/vllm-project/vllm), [LightLLM](https://github.com/ModelTC/lightllm), [FlashInfer](https://github.com/flashinfer-ai/flashinfer), [Outlines](https://github.com/outlines-dev/outlines), [LMQL](https://github.com/eth-sri/lmql).