From 3bed56bb13996abfa1aca8ccebd5bf4705aedb38 Mon Sep 17 00:00:00 2001
From: comfyanonymous <comfyanonymous@protonmail.com>
Date: Wed, 4 Dec 2024 07:11:16 -0500
Subject: [PATCH] Add another ROCm tip.

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

diff --git a/README.md b/README.md
index f88d63f2..bf7803ba 100644
--- a/README.md
+++ b/README.md
@@ -219,6 +219,8 @@ You can enable experimental memory efficient attention on pytorch 2.5 in ComfyUI
 
 ```TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 python main.py --use-pytorch-cross-attention```
 
+You can also try setting this env variable `PYTORCH_TUNABLEOP_ENABLED=1` which might speed things up at the cost of a very slow initial run.
+
 # Notes
 
 Only parts of the graph that have an output with all the correct inputs will be executed.