From 7b2f1845179451b2a7b1a1fe781ec15ebcbb24ff Mon Sep 17 00:00:00 2001
From: luix93 <76565668+luix93@users.noreply.github.com>
Date: Sat, 28 Mar 2026 16:51:43 +0100
Subject: [PATCH] Update CUDA_MODULE_LOADING to use LAZY

Changed CUDA module loading strategy from EAGER to LAZY for improved model loading speed.
---
 docker-compose.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docker-compose.yml b/docker-compose.yml
index 543be2d..52d95a2 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -42,7 +42,7 @@ services:
       PYTORCH_NO_CUDA_MEMORY_CACHING: "1"
       CUDA_DEVICE_MAX_CONNECTIONS: "1"
       CUDA_DEVICE_MAX_COPY_CONNECTIONS: "4"
-      CUDA_MODULE_LOADING: "CUDA" # EAGER works as well, however CUDA loads models in memory a lot faster
+      CUDA_MODULE_LOADING: "LAZY" # EAGER works as well, however LAZY loads models in memory a lot faster
       CUDA_MANAGED_FORCE_DEVICE_ALLOC: "1"
       OMP_NUM_THREADS: "20"
       CUBLAS_WORKSPACE_CONFIG: ":0:0"