On jetpack6.2, cant start riva_start.sh ...retrying in 10 seconds

[AastaLLL]

Hi,

Please apply following changes:

1. Downgrade docker to v27.5.1 to get iptables support

$ sudo apt-get install -y docker-ce=5:27.5* docker-ce-cli=5:27.5* --allow-downgrades

2. Create the models folder manually

$ mkdir model_repository/models

3. Replace --gpus with --runtime=nvidia:

diff --git a/riva_start.sh b/riva_start.sh
index 8ad07a9..0cbdb07 100644
--- a/riva_start.sh
+++ b/riva_start.sh
@@ -101,7 +101,7 @@ if [ $(docker ps -q -f "name=^/$riva_daemon_speech$" | wc -l) -eq 0 ]; then
     docker run -d \
         --init \
         --ipc=host \
-        --gpus '"'$gpus_to_use'"' \
+        --runtime=nvidia \
         -p $riva_speech_api_port:$riva_speech_api_port \
         -p $riva_speech_api_http_port:$riva_speech_api_http_port \
         -e RIVA_SERVER_HTTP_PORT=$riva_speech_api_http_port \

After applying the above changes, we can launch Riva server correctly:

$ sudo bash riva_start.sh 
Starting Riva Speech Services. This may take several minutes depending on the number of models deployed.
Waiting for Riva server to load all models...retrying in 10 seconds
Riva server is ready...
Use this container terminal to run applications:
root@3ce1ab67b283:/opt/riva#

Thanks.