From 8ae1f9b850a499eb7d55a04560ea90807d07b886 Mon Sep 17 00:00:00 2001
From: abetlen <abetlen@gmail.com>
Date: Tue, 24 Mar 2026 02:52:35 -0700
Subject: [PATCH] chore: bump version

---
 CHANGELOG.md          | 2 ++
 llama_cpp/__init__.py | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index de4f070ff..4118f4848 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]
 
+## [0.3.18]
+
 - feat: Expose `attention_type` in `Llama.__init__` for non-causal embedding models by @jamesbiederbeck in #2143
 - fix(ci): Build Docker images from the checked-out source and sanitize branch tags by @abetlen in #2156
 - fix(ci): Fix the CUDA wheel workflow and keep release tags aligned with the built toolkit by @abetlen in #2155
diff --git a/llama_cpp/__init__.py b/llama_cpp/__init__.py
index a7c40478b..bdaefb9e0 100644
--- a/llama_cpp/__init__.py
+++ b/llama_cpp/__init__.py
@@ -1,4 +1,4 @@
 from .llama_cpp import *
 from .llama import *
 
-__version__ = "0.3.17"
+__version__ = "0.3.18"