From fc36cbdfb688a060c473923ee074de09e4899f58 Mon Sep 17 00:00:00 2001
From: RVC-Boss <129054828+RVC-Boss@users.noreply.github.com>
Date: Tue, 21 Jul 2026 15:18:46 +0800
Subject: [PATCH] Update Changelog_EN.md

---
 docs/en/Changelog_EN.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/en/Changelog_EN.md b/docs/en/Changelog_EN.md
index 1dd2109..20ec90c 100644
--- a/docs/en/Changelog_EN.md
+++ b/docs/en/Changelog_EN.md
@@ -8,7 +8,7 @@
 - Single-GPU training no longer uses DDP.
 - The base model remains unchanged. Several issues affecting output quality have been fixed. Updating the bundled package/code and rerunning inference with an existing fine-tuned model, or retraining and then running inference with the new version, may improve results.
 - Added support for the FCPE pitch extraction algorithm.
-- Added support for CUDA Graph inference acceleration.
+- The real-time voice conversion GUI supports CUDA Graph inference acceleration, achieving up to a 4.7× speedup in algorithm inference latency (tested on an RTX 4090D), while GPU utilization remains around 20–30%.
 - Removed features that were clearly obsolete or no longer useful.
 
 ### 2023-10-06