From 60119dbaeb5a7d9eb6efc17137ac1d93ba33ffbe Mon Sep 17 00:00:00 2001
From: Andrei Betlen <abetlen@gmail.com>
Date: Wed, 13 Sep 2023 23:13:19 -0400
Subject: [PATCH] Update CHANGELOG

---
 CHANGELOG.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 8519489..d6a4037 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,10 +7,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+- 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
 - Added server params for `low_vram`, `main_gpu`, `lora_base`, and `lora_path` by @abetlen in 2920c4bf7ee1412d6bba7846e0e1b7ef6d34043b
 - Removed server params for `rms_norm_eps` and `n_gqa` by @abetlen in 2920c4bf7ee1412d6bba7846e0e1b7ef6d34043b
+- Fix boolean cli options by @abetlen in c999325e8e4507f6c6249dd2fb8de7f8bf57f71e and 0449d29b9f940e437231a07b9d56550226558bac
 
 ## [0.2.3]