NVIDIA GPU (Legacy)
As an additional Enterprise deployment, we offer an accelerated inference solution that you can deploy to your GPU devices.
Last updated
Was this helpful?
As an additional Enterprise deployment, we offer an accelerated inference solution that you can deploy to your GPU devices.
Last updated
Was this helpful?
This page is an outdated version of .
These deployment options require a .
To deploy the Enterprise GPU inference server, you must first install NVIDIA drivers and , allowing docker to passthrough your GPU to the inference server. You can test to see if your system already has nvidia-container-runtime
and if your installation was successful with the following command:
If your installation was successful, you will see your GPU device from within the container:
The last thing you need before building your GPU TRT container is your project information. This includes your Roboflow API Key, Model ID and Model Version. If you don't have this information you can follow this link to Locate Your Project Information. Once located, save those three variables for later.
The Enterprise GPU TRT deployment compiles your model on device, optimizing for the hardware that you have available. There are currently three deployment options for the GPU TRT container. Deploying to an EC2 instance via AWS, deploying to WSL2 via Windows, and deploying to Anaconda via Windows.
To run the TRT GPU container on an EC2 instance, you first need to select the proper AMI. The AMI can be configured when you are launching your instance and should be selected before you launch the instance. We are going to be using the NVIDIA GPU-Optimized AMI which comes with Ubuntu 20.04, Docker and other requirements pre-installed.
Once you are logged into the EC2 instance via SSH. We can start the Docker container with the following command:
Run inference on your model by posting a base64 encoded image to the server - if this is the first time you have compiled your model without cache, it will compile before inferring:
If you have installed Docker Desktop, make sure to have it running in order to access the container. Those of you that did not download Docker Desktop should be able to access the daemon version of Docker via our previous conda-forge
install process.
Once your Anaconda environment can successfully access Docker. We can start the Docker container with the following command:
Open up another Anaconda terminal and navigate to a directory that contains data you want to run inference on. Run inference on your model by posting a base64 encoded image to the server - if this is the first time you have compiled your model without cache, it will compile before inferring:
For those of you that want to run our TRT container on Windows, another option besides Anaconda is using WSL2. Windows Subsystem for Linux allows anyone with Windows 10+ to run Ubuntu asynchronously with Windows via a terminal interface. You can find it and download Ubuntu 20.04.5 in the Microsoft Store for free. After installation, run WSL2 by typing Ubuntu into your windows search bar and starting the application.
Once you have Docker successfully installed on your WSL2 environment, we can have Docker run the TRT container. To run the container, we need to use the command below which will start accepting inferences on port 9001.
Now that the GPU TRT container is running in Docker. We can open up another Ubuntu terminal which will be using to send inference data to the docker container. Use ls
and cd
Navigate to the location of an image you want to run inference on and use the command below.
If this is your first inference, your model will take some time to compile. Following inferences after the model is built will be faster.
In certain cases, you might want to cache your model locally so that each time the server starts it does not need to communicate with the external Roboflow servers to download your model.
To cache your model offline, first create a docker volume:
Then, start the server with your docker volume mounted on the /cache
directory:
We have developed a repository for quickly accessing examples on how to use the Roboflow TRT Docker container. To get started, run the git clone command below to download our docker compose template.
Make sure that the names of the services in the docker-compose.yaml file are correctly reflected in the .conf/roboflow-nginx.conf file then run docker compose.
Your Docker should now be spinning up multiple GPU containers that all share a volume and a port with the load balancer. This way the load balancer can manage the throughput of each container for optimal speed. If you are running in Docker Desktop, a successful boot up should look something like this.
Now that you have your GPU containers and the load balancer running. You are able to interact with the load balancer which will route all of your request to the respective GPU in order to maintain optimal throughput.
You can test the load balancer by opening up a new terminal and using one of the curl commands below.
To run less than the default 8 GPUs you will need to make some changes to a couple of the files in this repo. The first we will look at is the docker-compose.yaml which has a bunch of services such as Roboflow-GPU-1, Roboflow-GPU-2, etc. These services are what run the docker containers and attach to each GPU.
If we want to run only 3 GPUs, then we can delete all of the other services except for Roboflow-GPU-1, Roboflow-GPU-2 and Roboflow-GPU-3. To delete a service remove the line containing the service name and all the lines below it until the next service name.
The next file we need to edit would be the roboflow-nginx.conf which is found inside of the conf folder.
Continuing our example of going from 8 to 3 GPUs. We will need to remove some of the server lines of code in the upstream myapp1. Specifically line 17 through line 21 aren't necessary anymore because that would exceed our target number.
In some cases, you may have multiple camera streams that you want to process in parallel on the same TRT Container on the same GPU. To spin up multiple model services on in your TRT container specify the --env NUM_WORKERS=[desired num_workers]
On NVIDIA V100, we found that 2-4 workers provided optimal latency.
In certain cases, you may want your TRT container to run on a specific GPU or vGPU. You can do so by specifying CUDA_VISIBLE_DEVICES=[DESIRED GPU OR MIG ID]
First, check that your request contains the proper model version request parameters:
Check that the latest container is pulled:
sudo docker pull roboflow/inference-server-trt:latest
If using a cache volume, clear it:
sudo docker volume rm roboflow
sudo docker volume create roboflow
Re-check NVIDIA docker GPU drivers:
docker run --gpus all -it ubuntu nvidia-smi
Relaunch! If deployment errors persist, copy the server logs and send them to your Roboflow rep and we will jump in to help.
With your EC2 instance successfully running, we can log into it using SSH and our Amazon Keypair. Amazon provides the documentation for connecting to their instances . If you have your Keypair ready and know your EC2 instance's Public DNS, we can use the command below to log into the instance. The default instance-user-name
for this instance should be ubuntu.
To run the TRT container on or , we need to create our conda environment and install Docker. To create our environment we can use the commands below inside of the Anaconda terminal.
You can download and run docker via or you can install Docker via conda-forge
. The code below will install Docker using Anaconda's recipe manager.
Ubuntu 20.04.5 LTS should come with Docker installed, but just in case it doesn't, below are some useful commands for installing Docker in Ubuntu. Similar to the Anaconda installation, you may also run to bypass the need to install Docker. The full documentation can be found here:
For this example, we have configured the docker to run 8 GPUs with a load balancer. If you need to run less than 8 GPUs. We will cover that .
To build the load balancer docker container use the command below. If you want more information on the load balancer we are using you can find that information .
After you have changed these two files, you should be able to continue with the docker-compose tutorial by .