diff --git a/CHANGELOG.md b/CHANGELOG.md
index f9fd60f..22a85a1 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.4]
+
 - Add NUMA support. **NOTE** low level api users must call llama_backend_init at the start of their programs by abetlen in f4090a0bb2a2a25acfe28d31c82cc1aa273bedee
 - Fix tensor_split server cli argument by @abetlen in c4c440ba2dc86d9de728a751311fdd1c8e3756fa
 - Made all `Llama` init parameters into keyword-only parameters by @abetlen in c8f9b8a734b5b040379bbd93995ba177affab1fe
diff --git a/llama_cpp/__init__.py b/llama_cpp/__init__.py
index c284460..e1e8c72 100644
--- a/llama_cpp/__init__.py
+++ b/llama_cpp/__init__.py
@@ -1,4 +1,4 @@
 from .llama_cpp import *
 from .llama import *
 
-__version__ = "0.2.3"
\ No newline at end of file
+__version__ = "0.2.4"
\ No newline at end of file