Configuration - NVIDIA Docs

Riva ASR NIM uses docker containers under the hood. Each NIM is its own Docker container and there are several ways to configure it. The remainder of this section describes how to configure a NIM container.

GPU Selection

Passing --gpus all to docker run is not supported in environments with two or more GPUs.

In environments with a combination of GPUs, expose specific GPU inside the container using either:

the --gpus flag (ex: --gpus='"device=1")
the environment variable NVIDIA_VISIBLE_DEVICES (ex: -e NVIDIA_VISIBLE_DEVICES=1)

The device ID(s) to use as input(s) are listed in the output of nvidia-smi -L:

Copy
Copied!

            
            GPU 0: Tesla H100 (UUID: GPU-b404a1a1-d532-5b5c-20bc-b34e37f3ac46)
GPU 1: NVIDIA GeForce RTX 3080 (UUID: GPU-b404a1a1-d532-5b5c-20bc-b34e37f3ac46)

Refer to the NVIDIA Container Toolkit documentation for more instructions.

Shared memory flag

Tokenization uses Triton’s Python backend capabilities that scales with the number of CPU cores available. You may need to increase the available shared memory given to the microservice container.

Example providing 1g of shared memory:

Copy
Copied!

            
            docker run ... --shm-size=1g ...

Environment Variables

The following table describes the environment variables that can be passed into a NIM as a -e argument added to a docker run command:

ENV	Required?	Default	Notes
`NGC_API_KEY`	Yes	None	You must set this variable to the value of your personal NGC API key.
`NIM_CACHE_PATH`	Yes	`/opt/nim/.cache`	Location (in container) where the container caches model artifacts.
`NIM_HTTP_API_PORT`	Yes	`9000`	Publish the NIM service to the prescribed port inside the container. Make sure to adjust the port passed to the `-p/--publish` flag of docker run to reflect that (ex: `-p $NIM_HTTP_API_PORT:$NIM_HTTP_API_PORT`). The left-hand side of this `:` is your host address:port, and does NOT have to match with `$NIM_HTTP_API_PORT`. The right-hand side of the `:` is the port inside the container which MUST match `NIM_HTTP_API_PORT` (or `9000` if not set). Supported endpoints are `/v1/license` (Returns the license information), `/v1/metadata` (Returns metadata including asset information, license information, model information, and version) and `/v1/metrics` (Exposes Prometheus metrics via an ASGI app endpoint).
`NIM_GRPC_API_PORT`	Yes	`50051`	Publish the Riva ASR service over GRPC to the prescribed port inside the container. Make sure to adjust the port passed to the `-p/--publish` flag of docker run to reflect that (ex: `-p $NIM_GRPC_API_PORT:$NIM_GRPC_API_PORT`). The left-hand side of this `:` is your host address:port, and does NOT have to match with `$NIM_GRPC_API_PORT`. The right-hand side of the `:` is the port inside the container which MUST match `NIM_GRPC_API_PORT` (or `50051` if not set).

Volumes

The following table describes the paths inside the container into which local paths can be mounted.

Container path	Required	Notes	Docker argument example
`/opt/nim/.cache` (or `NIM_CACHE_PATH` if present)	Not required, but if this volume is not mounted, the container will do a fresh download of the model each time it is brought up.	This is the directory within which models are downloaded inside the container. It is very important that this directory could be accessed from inside the container. This can be achieved by adding the option `-u $(id -u)` to the `docker run` command. For example, to use `~/.cache/nim` as the host machine directory for caching models, first do `mkdir -p ~/.cache/nim` before running the `docker run ...` command.	`-v ~/.cache/nim:/opt/nim/.cache -u $(id -u)`