From 2bc11ac3a87337987b1e0cf6f11fb267fbb44dd2 Mon Sep 17 00:00:00 2001
From: abetlen <abetlen@gmail.com>
Date: Sun, 28 Jun 2026 21:15:57 -0700
Subject: [PATCH] chore: bump version to 0.3.32

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

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 9a7abb40fe..0b5e885784 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]
 
+## [0.3.32]
+
 - feat(example): support chained NextN heads for server MTP drafting
 - feat: update llama.cpp to ggml-org/llama.cpp@b3fed31b9
 - fix: preserve recurrent/hybrid model state when the full prompt is already cached by @allthatido and @abetlen in #2306
diff --git a/llama_cpp/__init__.py b/llama_cpp/__init__.py
index ed3c342f20..45f9c8f27f 100644
--- a/llama_cpp/__init__.py
+++ b/llama_cpp/__init__.py
@@ -1,4 +1,4 @@
 from .llama_cpp import *
 from .llama import *
 
-__version__ = "0.3.31"
+__version__ = "0.3.32"