From f21ef0d5de8f9c516a77548130f64378889bd7a8 Mon Sep 17 00:00:00 2001
From: ClashSAN <98228077+ClashSAN@users.noreply.github.com>
Date: Wed, 1 Mar 2023 00:55:26 +0000
Subject: [PATCH] make PYTORCH_CUDA_ALLOC_CONF enviornment variable placement
 easier to understand

---
 Optimizations.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Optimizations.md b/Optimizations.md
index 6594423..899e8d6 100644
--- a/Optimizations.md
+++ b/Optimizations.md
@@ -43,7 +43,7 @@ Notes:
 - Performance with `lowvram` preset is very low below batch size 8 and by then memory savings are not that big  
 
 Other possible optimizations:
-- `PYTORCH_CUDA_ALLOC_CONF=garbage_collection_threshold:0.9,max_split_size_mb:512`  
+- adding `set PYTORCH_CUDA_ALLOC_CONF=garbage_collection_threshold:0.9,max_split_size_mb:512` in `webui-user.bat`  
   No performance impact and increases initial memory footprint a bit but reduces memory fragmentation in long runs  
 - `opt-channelslast`  
   Hit-and-miss: seems like additional slight performance increase with higher batch sizes and slower with small sizes, but differences are within margin-of-error