From d85ed7f23e464b2657fff7dfe0cd3d79d87676bd Mon Sep 17 00:00:00 2001
From: Mikko Juola <mikjuo@gmail.com>
Date: Mon, 20 Mar 2023 18:29:44 -0700
Subject: [PATCH] Mention HTTP server in features in README.md

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

diff --git a/README.md b/README.md
index f34db17..1a1b3ad 100644
--- a/README.md
+++ b/README.md
@@ -8,6 +8,8 @@ RLLaMA is a pure Rust implementation of [LLaMA large language model inference.](
   * LLaMA-7B, LLaMA-13B, LLaMA-30B, LLaMA-65B all confirmed working
   * Hand-optimized AVX2 implementation
   * OpenCL support for GPU inference.
+  * Simple HTTP API support, with the possibility of doing token sampling on
+    client side
 
 ## Performance