diff --git a/Dockerfile b/Dockerfile
index 978fb85..3623f9c 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -13,7 +13,6 @@ WORKDIR /opt/gpu
 COPY 10-nvidia-runtime.toml 10-nvidia-runtime.toml 
 COPY 71-nvidia-char-dev.rules 71-nvidia-char-dev.rules
 COPY blacklist-nouveau.conf blacklist-nouveau.conf
-COPY nvidia-persistenced.service nvidia-persistenced.service
 
 COPY fm_run_package_installer.sh fm_run_package_installer.sh
 COPY config.sh config.sh
diff --git a/install.sh b/install.sh
index 26aede0..f8f5ef3 100644
--- a/install.sh
+++ b/install.sh
@@ -85,11 +85,7 @@ set -e
 dkms status
 nvidia-modprobe -u -c0
 
-# configure persistence daemon
-# decreases latency for later driver loads
-# reduces nvidia-smi invocation time 10x from 30 to 2 sec 
-# notable on large VM sizes with multiple GPUs
-# especially when nvidia-smi process is in CPU cgroup
+# copy nvidia userspace libs into the system library path so nvidia-smi can resolve them
 cp -r /usr/bin/lib64/lib64/* /usr/lib/$(uname -m)-linux-gnu/
 nvidia-smi
 
diff --git a/nvidia-persistenced.service b/nvidia-persistenced.service
deleted file mode 100644
index 82b932e..0000000
--- a/nvidia-persistenced.service
+++ /dev/null
@@ -1,12 +0,0 @@
-[Unit]
-Description=NVIDIA Persistence Daemon
-Wants=syslog.target
-
-[Service]
-Type=forking
-ExecStart=/usr/bin/nvidia-persistenced --verbose
-ExecStopPost=/bin/rm -rf /var/run/nvidia-persistenced
-Restart=always
-
-[Install]
-WantedBy=multi-user.target