diff --git a/docs/dev/architecture.md b/docs/dev/architecture.md index e0cb8c066..6195f23a9 100644 --- a/docs/dev/architecture.md +++ b/docs/dev/architecture.md @@ -85,13 +85,13 @@ NVCF supports four workload types on the compute plane: Each component ships an `AGENTS.md` with detailed internals, data flows, and API contracts: -- [`src/compute-plane-services/nvca/AGENTS.md`](../../src/compute-plane-services/nvca/AGENTS.md) -- [`src/compute-plane-services/ess-agent/AGENTS.md`](../../src/compute-plane-services/ess-agent/AGENTS.md) -- [`src/compute-plane-services/byoo-otel-collector/AGENTS.md`](../../src/compute-plane-services/byoo-otel-collector/AGENTS.md) -- [`src/invocation-plane-services/http-invocation/AGENTS.md`](../../src/invocation-plane-services/http-invocation/AGENTS.md) -- [`src/invocation-plane-services/grpc-proxy/AGENTS.md`](../../src/invocation-plane-services/grpc-proxy/AGENTS.md) -- [`src/invocation-plane-services/llm-api-gateway/AGENTS.md`](../../src/invocation-plane-services/llm-api-gateway/AGENTS.md) -- [`src/invocation-plane-services/ratelimiter/AGENTS.md`](../../src/invocation-plane-services/ratelimiter/AGENTS.md) -- [`src/control-plane-services/nats-auth-callout/AGENTS.md`](../../src/control-plane-services/nats-auth-callout/AGENTS.md) -- [`src/control-plane-services/function-autoscaler/AGENTS.md`](../../src/control-plane-services/function-autoscaler/AGENTS.md) -- [`examples/AGENTS.md`](../../examples/AGENTS.md) +- [src/compute-plane-services/nvca/AGENTS.md](https://github.com/NVIDIA/nvcf/blob/main/src/compute-plane-services/nvca/AGENTS.md) +- [src/compute-plane-services/ess-agent/AGENTS.md](https://github.com/NVIDIA/nvcf/blob/main/src/compute-plane-services/ess-agent/AGENTS.md) +- [src/compute-plane-services/byoo-otel-collector/AGENTS.md](https://github.com/NVIDIA/nvcf/blob/main/src/compute-plane-services/byoo-otel-collector/AGENTS.md) +- [src/invocation-plane-services/http-invocation/AGENTS.md](https://github.com/NVIDIA/nvcf/blob/main/src/invocation-plane-services/http-invocation/AGENTS.md) +- [src/invocation-plane-services/grpc-proxy/AGENTS.md](https://github.com/NVIDIA/nvcf/blob/main/src/invocation-plane-services/grpc-proxy/AGENTS.md) +- [src/invocation-plane-services/llm-api-gateway/AGENTS.md](https://github.com/NVIDIA/nvcf/blob/main/src/invocation-plane-services/llm-api-gateway/AGENTS.md) +- [src/invocation-plane-services/ratelimiter/AGENTS.md](https://github.com/NVIDIA/nvcf/blob/main/src/invocation-plane-services/ratelimiter/AGENTS.md) +- [src/control-plane-services/nats-auth-callout/AGENTS.md](https://github.com/NVIDIA/nvcf/blob/main/src/control-plane-services/nats-auth-callout/AGENTS.md) +- [src/control-plane-services/function-autoscaler/AGENTS.md](https://github.com/NVIDIA/nvcf/blob/main/src/control-plane-services/function-autoscaler/AGENTS.md) +- [examples/AGENTS.md](https://github.com/NVIDIA/nvcf/blob/main/examples/AGENTS.md) diff --git a/docs/dev/grpc-load-testing.md b/docs/dev/grpc-load-testing.md index c78c344f1..785e7a517 100644 --- a/docs/dev/grpc-load-testing.md +++ b/docs/dev/grpc-load-testing.md @@ -37,13 +37,13 @@ The `grpc_echo_sample` from the same repository shares the The source, build instructions, and registry push examples are in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/load_tester_supreme) +[NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/load-tester-supreme) repository. Build and push the image to whichever container registry your cluster has credentials for: ```bash -git clone https://github.com/NVIDIA/nv-cloud-function-helpers.git -cd nv-cloud-function-helpers/examples/function_samples/load_tester_supreme +git clone https://github.com/NVIDIA/nvcf.git +cd nvcf/examples/function-samples/load-tester-supreme # Build docker build --platform linux/amd64 -t load_tester_supreme . @@ -115,8 +115,8 @@ The CLI saves the function and version IDs automatically. Run ## Clone the load test scripts ```bash -git clone https://github.com/NVIDIA/nv-cloud-function-helpers.git -cd nv-cloud-function-helpers/examples/load-tests +git clone https://github.com/NVIDIA/nvcf.git +cd nvcf/examples/load-tests ``` ## Install k6 diff --git a/docs/dev/http-load-testing.md b/docs/dev/http-load-testing.md index 981ada37b..465fa6965 100644 --- a/docs/dev/http-load-testing.md +++ b/docs/dev/http-load-testing.md @@ -29,13 +29,13 @@ for high-throughput benchmarking and includes: - Built-in OpenTelemetry tracing The source, build instructions, and registry push examples are in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/load_tester_supreme) +[NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/load-tester-supreme) repository. Build and push the image to whichever container registry your cluster has credentials for: ```bash -git clone https://github.com/NVIDIA/nv-cloud-function-helpers.git -cd nv-cloud-function-helpers/examples/function_samples/load_tester_supreme +git clone https://github.com/NVIDIA/nvcf.git +cd nvcf/examples/function-samples/load-tester-supreme # Build docker build --platform linux/amd64 -t load_tester_supreme . @@ -100,8 +100,8 @@ k3d, Docker Desktop) it is typically `localhost` or `127.0.0.1`. ## Clone the load test scripts ```bash -git clone https://github.com/NVIDIA/nv-cloud-function-helpers.git -cd nv-cloud-function-helpers/examples/load-tests +git clone https://github.com/NVIDIA/nvcf.git +cd nvcf/examples/load-tests ``` ## Install k6 diff --git a/docs/dev/http-soak-testing.md b/docs/dev/http-soak-testing.md index 1a382266d..df7e4b727 100644 --- a/docs/dev/http-soak-testing.md +++ b/docs/dev/http-soak-testing.md @@ -32,13 +32,13 @@ for high-throughput benchmarking and includes: - Built-in OpenTelemetry tracing The source, build instructions, and registry push examples are in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/load_tester_supreme) +[NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/load-tester-supreme) repository. Build and push the image to whichever container registry your cluster has credentials for: ```bash -git clone https://github.com/NVIDIA/nv-cloud-function-helpers.git -cd nv-cloud-function-helpers/examples/function_samples/load_tester_supreme +git clone https://github.com/NVIDIA/nvcf.git +cd nvcf/examples/function-samples/load-tester-supreme # Build (multi-arch) docker buildx build --platform linux/amd64,linux/arm64 -t load_tester_supreme . @@ -162,7 +162,7 @@ you want a steady, predictable load. The latest version of this script is maintained in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers) +[NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples) repository. diff --git a/docs/ngc-managed/cluster-management/monitoring.md b/docs/ngc-managed/cluster-management/monitoring.md index 6a70b261e..922ec3764 100644 --- a/docs/ngc-managed/cluster-management/monitoring.md +++ b/docs/ngc-managed/cluster-management/monitoring.md @@ -21,7 +21,7 @@ The cluster agent and operator emit Prometheus-style metrics. The following metr | nvca_cluster_group | The NVCA cluster group | | nvca_version | The NVCA version | -Cluster maintainers can scrape the available metrics. See a full example of how to do this with an OpenTelemetry Collector in the cluster [here](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/cluster_monitoring_sample). +Cluster maintainers can scrape the available metrics. See a full example of how to do this with an OpenTelemetry Collector in the cluster [cluster monitoring example](https://github.com/NVIDIA/nvcf/tree/main/examples/cluster-monitoring-sample). Use the following examples of a PodMonitor for NVCA Operator and ServiceMonitor for NVCA for reference: diff --git a/docs/user/cli.md b/docs/user/cli.md index 4a53ef731..16d87a440 100644 --- a/docs/user/cli.md +++ b/docs/user/cli.md @@ -344,7 +344,7 @@ Or use the `--debug` flag or `NVCF_DEBUG=true` environment variable per-command. ``` -For immediate testing, you can use `load_tester_supreme` from `nvcf-onprem` (see [self-hosted-artifact-manifest](./manifest.md)), which supports the `{"message": "hello world"}` request body above. For more function samples, see the [nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers) repository and [function-creation](./function-creation.md) for function creation documentation. +For immediate testing, you can use `load_tester_supreme` from `nvcf-onprem` (see [self-hosted-artifact-manifest](./manifest.md)), which supports the `{"message": "hello world"}` request body above. For more function samples, see the [NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples) repository and [function-creation](./function-creation.md) for function creation documentation. diff --git a/docs/user/cluster-management/monitoring.md b/docs/user/cluster-management/monitoring.md index f7d829b57..c0fa6ae76 100644 --- a/docs/user/cluster-management/monitoring.md +++ b/docs/user/cluster-management/monitoring.md @@ -21,7 +21,7 @@ The cluster agent and operator emit Prometheus-style metrics. The following metr | nvca_cluster_group | The NVCA cluster group | | nvca_version | The NVCA version | -Cluster maintainers can scrape the available metrics. See a full example of how to do this with an OpenTelemetry Collector in the cluster [here](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/cluster_monitoring_sample). +Cluster maintainers can scrape the available metrics. See a full example of how to do this with an OpenTelemetry Collector in the cluster [cluster monitoring example](https://github.com/NVIDIA/nvcf/tree/main/examples/cluster-monitoring-sample). Use the following examples of a PodMonitor for NVCA Operator and ServiceMonitor for NVCA for reference: diff --git a/docs/user/container-functions.md b/docs/user/container-functions.md index 1cb6894d7..7552a4dbd 100644 --- a/docs/user/container-functions.md +++ b/docs/user/container-functions.md @@ -4,9 +4,9 @@ Container-based functions require building and pushing a Cloud Functions compati ## Resources -- Example containers can be found [in the examples repository](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples). +- Example containers can be found [in the examples directory](https://github.com/NVIDIA/nvcf/tree/main/examples). -- The repository also contains [helper functions](https://github.com/NVIDIA/nv-cloud-function-helpers/blob/main/helper_library/nv_cloud_function_helpers/nvcf_container/helpers.py) that are useful when authoring your container, including: +- The repository also contains [helper functions](https://github.com/NVIDIA/nvcf/blob/main/src/libraries/python/nv-cloud-function-helpers/nv_cloud_function_helpers/nvcf_container/helpers.py) that are useful when authoring your container, including: - Helpers that parse Cloud Functions-specific parameters on invocation - Helpers that can be used to instrument your container with Cloud Functions compatible logs @@ -43,7 +43,7 @@ Cloud Functions also expects the following directories in the container to remai ## Composing a FastAPI Container -It's possible to use any container with Cloud Functions as long as it implements a server with the above endpoints. The below is an example of a FastAPI-based container compatible with Cloud Functions. Clone the [FastAPI echo example](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/fastapi_echo_sample). +It's possible to use any container with Cloud Functions as long as it implements a server with the above endpoints. The below is an example of a FastAPI-based container compatible with Cloud Functions. Clone the [FastAPI echo example](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/fastapi-echo-sample). ### Create the "requirements.txt" File @@ -289,7 +289,7 @@ Create the function via the NVCF API. In this example, we defined the inference ### Additional Examples -See more examples of containers that are Cloud Functions compatible [in the function samples directory](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/). +See more examples of containers that are Cloud Functions compatible [in the function samples directory](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/). ## Creating gRPC-based Functions @@ -300,7 +300,7 @@ Cloud Functions supports function invocation via gRPC. During function creation, - The function container must implement a gRPC port, endpoint and health check. The health check is expected to be served by the gRPC inference port, there is no need to define a separate health endpoint path. - See [gRPC health checking](https://grpc.io/docs/guides/health-checking/). - - See an [example container](https://github.com/NVIDIA/nv-cloud-function-helpers/blob/main/examples/function_samples/grpc_echo_sample/grpc_echo_server.py) with a gRPC server that is Cloud Functions compatible. + - See an [example container](https://github.com/NVIDIA/nvcf/blob/main/examples/function-samples/grpc-echo-sample/grpc_echo_server.py) with a gRPC server that is Cloud Functions compatible. ### gRPC Function Creation via API diff --git a/docs/user/function-creation.md b/docs/user/function-creation.md index af728a90b..f8d593fd9 100644 --- a/docs/user/function-creation.md +++ b/docs/user/function-creation.md @@ -48,7 +48,7 @@ For LLM functions, see [LLM Gateway](./llm-gateway.md#function-configuration) fo The following is a reference of available variables via the headers of the invocation message (auto-populated by Cloud Functions), accessible within the container. -For examples of how to extract and use some of these variables, see [NVCF Container Helper Functions](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main). +For examples of how to extract and use some of these variables, see [NVCF Container Helper Functions](https://github.com/NVIDIA/nvcf/tree/main/src/libraries/python/nv-cloud-function-helpers). | Name | Description | | ---------------------------- | ------------------------------------------------------- | diff --git a/docs/user/helm-functions.md b/docs/user/helm-functions.md index 509f8f64b..ecd2b748a 100644 --- a/docs/user/helm-functions.md +++ b/docs/user/helm-functions.md @@ -41,7 +41,7 @@ All Pod specs in your helm chart will be updated with pull secrets at runtime, s **Example Creation via API** -Please see our [sample helm chart used](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/helmchart_samples/inference_test_sample) in this example for reference. +Please see our [sample helm chart used](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/helmchart-samples/inference-test-sample) in this example for reference. Below is an example function creation API call creating a helm-based function: @@ -72,7 +72,7 @@ For gRPC-based functions, set `"inferenceURL" : "/gRPC"`. This signals to Cloud To create a multi-node helm deployment, you need to use the following format for the `instanceType`: `.GPU._x[.x]`. For example, `DGXC.GPU.L40S_1x` is a single L40S instance while `ON-PREM.GPU.B200_8x.x2` is two full nodes of 8-way B200. -A sample helm chart for a multi-node deployment can be found [in the multi-node helm example](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/helmchart_samples/multi_node_helm_function_test/). +A sample helm chart for a multi-node deployment can be found [in the multi-node helm example](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/helmchart-samples/multi-node-helm-function-test/). ## Limitations diff --git a/docs/user/helmfile-installation.md b/docs/user/helmfile-installation.md index 3cd69b295..9ed3af914 100644 --- a/docs/user/helmfile-installation.md +++ b/docs/user/helmfile-installation.md @@ -191,7 +191,7 @@ Environment configuration files define how NVCF is deployed in your specific env Set `HELMFILE_ENV` to your environment name and copy the base configuration. The filename must match `HELMFILE_ENV` because Helmfile uses it to select the environment file. The template below shows the values to configure for Amazon -EKS ([cp-env-eks-example.yaml](samples/configs/cp-env-eks-example.yaml)). +EKS ([cp-env-eks-example.yaml](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/user/samples/configs/cp-env-eks-example.yaml)). ```bash cd path/to/nvcf-self-managed-stack @@ -586,7 +586,7 @@ These credentials will then be used for function deployments. Note that if the r Copy the secrets template using the same `HELMFILE_ENV` value from Step 2. The filename must match `HELMFILE_ENV` because Helmfile loads the corresponding secrets file. The example below shows the required structure -([example-secrets.yaml](samples/configs/cp-example-secrets.yaml)). You must +([example-secrets.yaml](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/user/samples/configs/cp-example-secrets.yaml)). You must replace all instances of `REPLACE_WITH_BASE64_DOCKER_CREDENTIAL` with your actual base64-encoded registry credentials. @@ -731,7 +731,7 @@ registry. If your `image` registry is private and your cluster nodes do not have built-in credential helpers, you must create Kubernetes `docker-registry` secrets in each NVCF namespace and configure the helmfile to reference them. 1. Create the pull secret in each NVCF namespace - ([create-nvcr-pull-secrets.sh](samples/scripts/create-nvcr-pull-secrets.sh)): + ([create-nvcr-pull-secrets.sh](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/user/samples/scripts/create-nvcr-pull-secrets.sh)): ```bash export NGC_API_KEY="" diff --git a/docs/user/observability.md b/docs/user/observability.md index 8d8150ba5..0a6520801 100644 --- a/docs/user/observability.md +++ b/docs/user/observability.md @@ -295,7 +295,7 @@ Dashboards are provided in native Grafana JSON format for [file-provisioning](ht Load dashboards into Grafana by placing them in `/etc/grafana/provisioning/dashboards/` on startup. Published dashboards will be available in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers) public GitHub repository. +[NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples) public GitHub repository. ## Troubleshooting diff --git a/docs/user/troubleshooting.md b/docs/user/troubleshooting.md index 30942181c..11a5c10c2 100644 --- a/docs/user/troubleshooting.md +++ b/docs/user/troubleshooting.md @@ -1090,7 +1090,7 @@ echo "==============================================" ``` -[force-cleanup-nvcf.sh](samples/scripts/force-cleanup-nvcf.sh) +[force-cleanup-nvcf.sh](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/user/samples/scripts/force-cleanup-nvcf.sh) **Usage:** diff --git a/docs/v0.5/cli.md b/docs/v0.5/cli.md index be905c5a8..307675416 100644 --- a/docs/v0.5/cli.md +++ b/docs/v0.5/cli.md @@ -274,7 +274,7 @@ Or use the `--debug` flag or `NVCF_DEBUG=true` environment variable per-command. ``` -For immediate testing, you can use `load_tester_supreme` from `nvcf-onprem` (see [self-hosted-artifact-manifest](./manifest.md)), which supports the `{"message": "hello world"}` request body above. For more function samples, see the [nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers) repository and [function-creation](./function-creation.md) for function creation documentation. +For immediate testing, you can use `load_tester_supreme` from `nvcf-onprem` (see [self-hosted-artifact-manifest](./manifest.md)), which supports the `{"message": "hello world"}` request body above. For more function samples, see the [NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples) repository and [function-creation](./function-creation.md) for function creation documentation. diff --git a/docs/v0.5/cluster-management/monitoring.md b/docs/v0.5/cluster-management/monitoring.md index f7d829b57..c0fa6ae76 100644 --- a/docs/v0.5/cluster-management/monitoring.md +++ b/docs/v0.5/cluster-management/monitoring.md @@ -21,7 +21,7 @@ The cluster agent and operator emit Prometheus-style metrics. The following metr | nvca_cluster_group | The NVCA cluster group | | nvca_version | The NVCA version | -Cluster maintainers can scrape the available metrics. See a full example of how to do this with an OpenTelemetry Collector in the cluster [here](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/cluster_monitoring_sample). +Cluster maintainers can scrape the available metrics. See a full example of how to do this with an OpenTelemetry Collector in the cluster [cluster monitoring example](https://github.com/NVIDIA/nvcf/tree/main/examples/cluster-monitoring-sample). Use the following examples of a PodMonitor for NVCA Operator and ServiceMonitor for NVCA for reference: diff --git a/docs/v0.5/container-functions.md b/docs/v0.5/container-functions.md index feb524a49..c0e0629b5 100644 --- a/docs/v0.5/container-functions.md +++ b/docs/v0.5/container-functions.md @@ -4,9 +4,9 @@ Container-based functions require building and pushing a Cloud Functions compati ## Resources -- Example containers can be found [in the examples repository](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples). +- Example containers can be found [in the examples directory](https://github.com/NVIDIA/nvcf/tree/main/examples). -- The repository also contains [helper functions](https://github.com/NVIDIA/nv-cloud-function-helpers/blob/main/helper_library/nv_cloud_function_helpers/nvcf_container/helpers.py) that are useful when authoring your container, including: +- The repository also contains [helper functions](https://github.com/NVIDIA/nvcf/blob/main/src/libraries/python/nv-cloud-function-helpers/nv_cloud_function_helpers/nvcf_container/helpers.py) that are useful when authoring your container, including: - Helpers that parse Cloud Functions-specific parameters on invocation - Helpers that can be used to instrument your container with Cloud Functions compatible logs @@ -43,7 +43,7 @@ Cloud Functions also expects the following directories in the container to remai ## Composing a FastAPI Container -It's possible to use any container with Cloud Functions as long as it implements a server with the above endpoints. The below is an example of a FastAPI-based container compatible with Cloud Functions. Clone the [FastAPI echo example](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/fastapi_echo_sample). +It's possible to use any container with Cloud Functions as long as it implements a server with the above endpoints. The below is an example of a FastAPI-based container compatible with Cloud Functions. Clone the [FastAPI echo example](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/fastapi-echo-sample). ### Create the "requirements.txt" File @@ -289,7 +289,7 @@ Create the function via the NVCF API. In this example, we defined the inference ### Additional Examples -See more examples of containers that are Cloud Functions compatible [in the function samples directory](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/). +See more examples of containers that are Cloud Functions compatible [in the function samples directory](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/). ## Creating gRPC-based Functions @@ -300,7 +300,7 @@ Cloud Functions supports function invocation via gRPC. During function creation, - The function container must implement a gRPC port, endpoint and health check. The health check is expected to be served by the gRPC inference port, there is no need to define a separate health endpoint path. - See [gRPC health checking](https://grpc.io/docs/guides/health-checking/). - - See an [example container](https://github.com/NVIDIA/nv-cloud-function-helpers/blob/main/examples/function_samples/grpc_echo_sample/grpc_echo_server.py) with a gRPC server that is Cloud Functions compatible. + - See an [example container](https://github.com/NVIDIA/nvcf/blob/main/examples/function-samples/grpc-echo-sample/grpc_echo_server.py) with a gRPC server that is Cloud Functions compatible. ### gRPC Function Creation via API @@ -321,4 +321,4 @@ When creating the gRPC function, set the `inferenceUrl` field to `/grpc`: ### gRPC Function Invocation -gRPC function invocation uses the same `Authorization: Bearer $NVCF_TOKEN` header as HTTP invocation, passed as gRPC metadata. See the [gRPC invocation examples](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples) for details on how to authenticate and invoke your gRPC function. +gRPC function invocation uses the same `Authorization: Bearer $NVCF_TOKEN` header as HTTP invocation, passed as gRPC metadata. See the [gRPC invocation examples](https://github.com/NVIDIA/nvcf/tree/main/examples) for details on how to authenticate and invoke your gRPC function. diff --git a/docs/v0.5/function-creation.md b/docs/v0.5/function-creation.md index 0908d8063..3491753c0 100644 --- a/docs/v0.5/function-creation.md +++ b/docs/v0.5/function-creation.md @@ -35,7 +35,7 @@ Additionally, Cloud Functions supports [Low Latency Streaming (LLS) functions](. The following is a reference of available variables via the headers of the invocation message (auto-populated by Cloud Functions), accessible within the container. -For examples of how to extract and use some of these variables, see [NVCF Container Helper Functions](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main). +For examples of how to extract and use some of these variables, see [NVCF Container Helper Functions](https://github.com/NVIDIA/nvcf/tree/main/src/libraries/python/nv-cloud-function-helpers). | Name | Description | | ---------------------------- | ------------------------------------------------------- | diff --git a/docs/v0.5/grpc-load-testing.md b/docs/v0.5/grpc-load-testing.md index 9ba7443e7..db4b71b6c 100644 --- a/docs/v0.5/grpc-load-testing.md +++ b/docs/v0.5/grpc-load-testing.md @@ -37,13 +37,13 @@ The `grpc_echo_sample` from the same repository shares the The source, build instructions, and registry push examples are in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/load_tester_supreme) +[NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/load-tester-supreme) repository. Build and push the image to whichever container registry your cluster has credentials for: ```bash -git clone https://github.com/NVIDIA/nv-cloud-function-helpers.git -cd nv-cloud-function-helpers/examples/function_samples/load_tester_supreme +git clone https://github.com/NVIDIA/nvcf.git +cd nvcf/examples/function-samples/load-tester-supreme # Build docker build --platform linux/amd64 -t load_tester_supreme . @@ -111,8 +111,8 @@ The CLI saves the function and version IDs automatically. Run ## Clone the load test scripts ```bash -git clone https://github.com/NVIDIA/nv-cloud-function-helpers.git -cd nv-cloud-function-helpers/examples/load-tests +git clone https://github.com/NVIDIA/nvcf.git +cd nvcf/examples/load-tests ``` ## Install k6 diff --git a/docs/v0.5/helm-functions.md b/docs/v0.5/helm-functions.md index 509f8f64b..ecd2b748a 100644 --- a/docs/v0.5/helm-functions.md +++ b/docs/v0.5/helm-functions.md @@ -41,7 +41,7 @@ All Pod specs in your helm chart will be updated with pull secrets at runtime, s **Example Creation via API** -Please see our [sample helm chart used](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/helmchart_samples/inference_test_sample) in this example for reference. +Please see our [sample helm chart used](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/helmchart-samples/inference-test-sample) in this example for reference. Below is an example function creation API call creating a helm-based function: @@ -72,7 +72,7 @@ For gRPC-based functions, set `"inferenceURL" : "/gRPC"`. This signals to Cloud To create a multi-node helm deployment, you need to use the following format for the `instanceType`: `.GPU._x[.x]`. For example, `DGXC.GPU.L40S_1x` is a single L40S instance while `ON-PREM.GPU.B200_8x.x2` is two full nodes of 8-way B200. -A sample helm chart for a multi-node deployment can be found [in the multi-node helm example](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/helmchart_samples/multi_node_helm_function_test/). +A sample helm chart for a multi-node deployment can be found [in the multi-node helm example](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/helmchart-samples/multi-node-helm-function-test/). ## Limitations diff --git a/docs/v0.5/helmfile-installation.md b/docs/v0.5/helmfile-installation.md index 7096860ce..e2ad95459 100644 --- a/docs/v0.5/helmfile-installation.md +++ b/docs/v0.5/helmfile-installation.md @@ -259,7 +259,7 @@ The Gateway you created here will be used by the `nvcf-gateway-routes` chart to Environment configuration files define how NVCF is deployed in your specific environment. They are YAML files that provide values to the Helm charts. -Create your environment file from the template below ([cp-env-eks-example.yaml](samples/configs/cp-env-eks-example.yaml)). +Create your environment file from the template below ([cp-env-eks-example.yaml](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/cp-env-eks-example.yaml)). ```bash cd path/to/nvcf-self-managed-stack @@ -606,7 +606,7 @@ Secrets configuration contains any sensitive data required for NVCF operation. T These credentials will then be used for function deployments. Note that if the registry credentials are not correct you can always update them using the steps in [third-party-registries-self-hosted](./third-party-registries.md). -Create your secrets file from the template below ([example-secrets.yaml](samples/configs/cp-example-secrets.yaml)). You must replace all instances of `REPLACE_WITH_BASE64_DOCKER_CREDENTIAL` with your actual base64-encoded registry credentials. +Create your secrets file from the template below ([example-secrets.yaml](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/cp-example-secrets.yaml)). You must replace all instances of `REPLACE_WITH_BASE64_DOCKER_CREDENTIAL` with your actual base64-encoded registry credentials. ```bash cd path/to/nvcf-self-managed-stack @@ -727,7 +727,7 @@ The secrets file you configured in Step 3 handles **API bootstrap registry crede If your `image` registry is private and your cluster nodes do not have built-in credential helpers, you must create Kubernetes `docker-registry` secrets in each NVCF namespace and configure the helmfile to reference them. -**1. Create the pull secret** in each NVCF namespace ([create-nvcr-pull-secrets.sh](samples/scripts/create-nvcr-pull-secrets.sh)): +**1. Create the pull secret** in each NVCF namespace ([create-nvcr-pull-secrets.sh](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/scripts/create-nvcr-pull-secrets.sh)): ```bash export NGC_API_KEY="" diff --git a/docs/v0.5/http-soak-testing.md b/docs/v0.5/http-soak-testing.md index 8b36a7a4d..9527ebf43 100644 --- a/docs/v0.5/http-soak-testing.md +++ b/docs/v0.5/http-soak-testing.md @@ -32,13 +32,13 @@ for high-throughput benchmarking and includes: - Built-in OpenTelemetry tracing The source, build instructions, and registry push examples are in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/load_tester_supreme) +[NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/load-tester-supreme) repository. Build and push the image to whichever container registry your cluster has credentials for: ```bash -git clone https://github.com/NVIDIA/nv-cloud-function-helpers.git -cd nv-cloud-function-helpers/examples/function_samples/load_tester_supreme +git clone https://github.com/NVIDIA/nvcf.git +cd nvcf/examples/function-samples/load-tester-supreme # Build (multi-arch) docker buildx build --platform linux/amd64,linux/arm64 -t load_tester_supreme . @@ -163,7 +163,7 @@ you want a steady, predictable load. The latest version of this script is maintained in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers) +[NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples) repository. diff --git a/docs/v0.5/local-development.md b/docs/v0.5/local-development.md index c525d1268..3ada6dd72 100644 --- a/docs/v0.5/local-development.md +++ b/docs/v0.5/local-development.md @@ -23,10 +23,10 @@ and adjust the pull secret configuration accordingly. See [self-hosted-image-mir for details on mirroring artifacts to other registries. -A ready-to-use k3d configuration and setup script is available in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/self_hosted_local_development) -repository. Clone it and run `./setup.sh` to create the cluster with all prerequisites, -then skip to [Deploy the NVCF Stack]. +A ready-to-use k3d configuration and Makefile is available in +[tools/ncp-local-cluster](https://github.com/NVIDIA/nvcf/tree/main/tools/ncp-local-cluster) +in the NVCF repository. Clone the repo, then run `make` from that directory to create +the cluster with all prerequisites, then skip to [Deploy the NVCF Stack]. @@ -160,7 +160,7 @@ k3d handles LoadBalancer services automatically via its built-in `klipper-lb`. ## Step 2 (Environment file) Create a local development environment file from the template below -([local-dev-env.yaml](samples/configs/local-dev-env.yaml)). +([local-dev-env.yaml](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/local-dev-env.yaml)). Save it as `environments/.yaml` (e.g., `environments/my-local.yaml`) in your `nvcf-self-managed-stack` directory. diff --git a/docs/v0.5/observability.md b/docs/v0.5/observability.md index b061f1336..3bdbac126 100644 --- a/docs/v0.5/observability.md +++ b/docs/v0.5/observability.md @@ -234,7 +234,7 @@ Dashboards are provided in native Grafana JSON format for [file-provisioning](ht Load dashboards into Grafana by placing them in `/etc/grafana/provisioning/dashboards/` on startup. Published dashboards will be available in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers) public GitHub repository. +[NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples) public GitHub repository. ## Troubleshooting diff --git a/docs/v0.5/standalone-core-services.md b/docs/v0.5/standalone-core-services.md index 2185685b9..0116b77e8 100644 --- a/docs/v0.5/standalone-core-services.md +++ b/docs/v0.5/standalone-core-services.md @@ -28,7 +28,7 @@ API Keys provides authentication token management for all NVCF API interactions. ### Configuration -Create `api-keys-values.yaml` ([download template](samples/configs/standalone/api-keys-values.yaml)): +Create `api-keys-values.yaml` ([download template](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/standalone/api-keys-values.yaml)): ```yaml title="api-keys-values.yaml" @@ -80,7 +80,7 @@ The Spot Instance Service (SIS) handles cluster registration and GPU resource ma ### Configuration -Create `sis-values.yaml` ([download template](samples/configs/standalone/sis-values.yaml)): +Create `sis-values.yaml` ([download template](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/standalone/sis-values.yaml)): ```yaml title="sis-values.yaml" @@ -130,7 +130,7 @@ The ESS (Enterprise Secrets Service) API distributes secrets to NVCF services vi ### Configuration -Create `ess-api-values.yaml` ([download template](samples/configs/standalone/ess-api-values.yaml)): +Create `ess-api-values.yaml` ([download template](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/standalone/ess-api-values.yaml)): ```yaml title="ess-api-values.yaml" @@ -184,7 +184,7 @@ communicates with ESS during initialization. ### Configuration -Create `nvcf-api-values.yaml` ([download template](samples/configs/standalone/nvcf-api-values.yaml)): +Create `nvcf-api-values.yaml` ([download template](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/standalone/nvcf-api-values.yaml)): ```yaml title="nvcf-api-values.yaml" @@ -324,7 +324,7 @@ The Invocation Service handles function invocation requests and routes them to w ### Configuration -Create `invocation-service-values.yaml` ([download template](samples/configs/standalone/invocation-service-values.yaml)): +Create `invocation-service-values.yaml` ([download template](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/standalone/invocation-service-values.yaml)): ```yaml title="invocation-service-values.yaml" @@ -374,7 +374,7 @@ The gRPC Proxy enables streaming workloads over gRPC connections. ### Configuration -Create `grpc-proxy-values.yaml` ([download template](samples/configs/standalone/grpc-proxy-values.yaml)): +Create `grpc-proxy-values.yaml` ([download template](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/standalone/grpc-proxy-values.yaml)): ```yaml title="grpc-proxy-values.yaml" @@ -424,7 +424,7 @@ The Notary Service handles request signing and validation for secure inter-servi ### Configuration -Create `notary-service-values.yaml` ([download template](samples/configs/standalone/notary-service-values.yaml)): +Create `notary-service-values.yaml` ([download template](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/standalone/notary-service-values.yaml)): ```yaml title="notary-service-values.yaml" @@ -475,7 +475,7 @@ installed in the `nvcf` namespace with the `helm-reval` chart. ### Configuration -Create `reval-values.yaml` ([download template](samples/configs/standalone/reval-values.yaml)): +Create `reval-values.yaml` ([download template](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/standalone/reval-values.yaml)): ```yaml title="reval-values.yaml" @@ -528,7 +528,7 @@ requiring pre-existing credentials. It is used for initial setup and emergency a ### Configuration -Create `admin-issuer-proxy-values.yaml` ([download template](samples/configs/standalone/admin-issuer-proxy-values.yaml)): +Create `admin-issuer-proxy-values.yaml` ([download template](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/standalone/admin-issuer-proxy-values.yaml)): ```yaml title="admin-issuer-proxy-values.yaml" diff --git a/docs/v0.5/standalone-gateway.md b/docs/v0.5/standalone-gateway.md index b300d0eb8..7913c7734 100644 --- a/docs/v0.5/standalone-gateway.md +++ b/docs/v0.5/standalone-gateway.md @@ -139,7 +139,7 @@ to NVCF services through the Gateway. ### Configuration -Create `gateway-routes-values.yaml` ([download template](samples/configs/standalone/gateway-routes-values.yaml)): +Create `gateway-routes-values.yaml` ([download template](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/standalone/gateway-routes-values.yaml)): ```yaml title="gateway-routes-values.yaml" diff --git a/docs/v0.5/standalone-infrastructure.md b/docs/v0.5/standalone-infrastructure.md index 140942178..35682c7e8 100644 --- a/docs/v0.5/standalone-infrastructure.md +++ b/docs/v0.5/standalone-infrastructure.md @@ -23,7 +23,7 @@ components. ### Configuration -Create `nats-values.yaml` with your registry settings ([download template](samples/configs/standalone/nats-values.yaml)): +Create `nats-values.yaml` with your registry settings ([download template](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/standalone/nats-values.yaml)): @@ -135,7 +135,7 @@ communicates with NATS during initialization. ### Configuration -Create `openbao-values.yaml` with your registry and secret settings ([download template](samples/configs/standalone/openbao-values.yaml)): +Create `openbao-values.yaml` with your registry and secret settings ([download template](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/standalone/openbao-values.yaml)): @@ -358,7 +358,7 @@ deployment state, and other operational data. ### Configuration -Create `cassandra-values.yaml` with your registry and storage settings ([download template](samples/configs/standalone/cassandra-values.yaml)): +Create `cassandra-values.yaml` with your registry and storage settings ([download template](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/configs/standalone/cassandra-values.yaml)): diff --git a/docs/v0.5/troubleshooting.md b/docs/v0.5/troubleshooting.md index 8d251dc05..081539b01 100644 --- a/docs/v0.5/troubleshooting.md +++ b/docs/v0.5/troubleshooting.md @@ -855,7 +855,7 @@ echo "==============================================" ``` -[force-cleanup-nvcf.sh](samples/scripts/force-cleanup-nvcf.sh) +[force-cleanup-nvcf.sh](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.5/samples/scripts/force-cleanup-nvcf.sh) **Usage:** diff --git a/docs/v0.6.0/cli.md b/docs/v0.6.0/cli.md index 85b6364dd..a84be034c 100644 --- a/docs/v0.6.0/cli.md +++ b/docs/v0.6.0/cli.md @@ -337,7 +337,7 @@ Or use the `--debug` flag or `NVCF_DEBUG=true` environment variable per-command. ``` -For immediate testing, you can use `load_tester_supreme` from `nvcf-onprem` (see [self-hosted-artifact-manifest](./manifest.md)), which supports the `{"message": "hello world"}` request body above. For more function samples, see the [nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers) repository and [function-creation](./function-creation.md) for function creation documentation. +For immediate testing, you can use `load_tester_supreme` from `nvcf-onprem` (see [self-hosted-artifact-manifest](./manifest.md)), which supports the `{"message": "hello world"}` request body above. For more function samples, see the [NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples) repository and [function-creation](./function-creation.md) for function creation documentation. diff --git a/docs/v0.6.0/cluster-management/monitoring.md b/docs/v0.6.0/cluster-management/monitoring.md index f7d829b57..c0fa6ae76 100644 --- a/docs/v0.6.0/cluster-management/monitoring.md +++ b/docs/v0.6.0/cluster-management/monitoring.md @@ -21,7 +21,7 @@ The cluster agent and operator emit Prometheus-style metrics. The following metr | nvca_cluster_group | The NVCA cluster group | | nvca_version | The NVCA version | -Cluster maintainers can scrape the available metrics. See a full example of how to do this with an OpenTelemetry Collector in the cluster [here](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/cluster_monitoring_sample). +Cluster maintainers can scrape the available metrics. See a full example of how to do this with an OpenTelemetry Collector in the cluster [cluster monitoring example](https://github.com/NVIDIA/nvcf/tree/main/examples/cluster-monitoring-sample). Use the following examples of a PodMonitor for NVCA Operator and ServiceMonitor for NVCA for reference: diff --git a/docs/v0.6.0/container-functions.md b/docs/v0.6.0/container-functions.md index 1cb6894d7..7552a4dbd 100644 --- a/docs/v0.6.0/container-functions.md +++ b/docs/v0.6.0/container-functions.md @@ -4,9 +4,9 @@ Container-based functions require building and pushing a Cloud Functions compati ## Resources -- Example containers can be found [in the examples repository](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples). +- Example containers can be found [in the examples directory](https://github.com/NVIDIA/nvcf/tree/main/examples). -- The repository also contains [helper functions](https://github.com/NVIDIA/nv-cloud-function-helpers/blob/main/helper_library/nv_cloud_function_helpers/nvcf_container/helpers.py) that are useful when authoring your container, including: +- The repository also contains [helper functions](https://github.com/NVIDIA/nvcf/blob/main/src/libraries/python/nv-cloud-function-helpers/nv_cloud_function_helpers/nvcf_container/helpers.py) that are useful when authoring your container, including: - Helpers that parse Cloud Functions-specific parameters on invocation - Helpers that can be used to instrument your container with Cloud Functions compatible logs @@ -43,7 +43,7 @@ Cloud Functions also expects the following directories in the container to remai ## Composing a FastAPI Container -It's possible to use any container with Cloud Functions as long as it implements a server with the above endpoints. The below is an example of a FastAPI-based container compatible with Cloud Functions. Clone the [FastAPI echo example](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/fastapi_echo_sample). +It's possible to use any container with Cloud Functions as long as it implements a server with the above endpoints. The below is an example of a FastAPI-based container compatible with Cloud Functions. Clone the [FastAPI echo example](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/fastapi-echo-sample). ### Create the "requirements.txt" File @@ -289,7 +289,7 @@ Create the function via the NVCF API. In this example, we defined the inference ### Additional Examples -See more examples of containers that are Cloud Functions compatible [in the function samples directory](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/). +See more examples of containers that are Cloud Functions compatible [in the function samples directory](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/). ## Creating gRPC-based Functions @@ -300,7 +300,7 @@ Cloud Functions supports function invocation via gRPC. During function creation, - The function container must implement a gRPC port, endpoint and health check. The health check is expected to be served by the gRPC inference port, there is no need to define a separate health endpoint path. - See [gRPC health checking](https://grpc.io/docs/guides/health-checking/). - - See an [example container](https://github.com/NVIDIA/nv-cloud-function-helpers/blob/main/examples/function_samples/grpc_echo_sample/grpc_echo_server.py) with a gRPC server that is Cloud Functions compatible. + - See an [example container](https://github.com/NVIDIA/nvcf/blob/main/examples/function-samples/grpc-echo-sample/grpc_echo_server.py) with a gRPC server that is Cloud Functions compatible. ### gRPC Function Creation via API diff --git a/docs/v0.6.0/function-creation.md b/docs/v0.6.0/function-creation.md index 7f46d73db..b1091e75f 100644 --- a/docs/v0.6.0/function-creation.md +++ b/docs/v0.6.0/function-creation.md @@ -48,7 +48,7 @@ For LLM functions, see [LLM Gateway](./llm-gateway.md#function-configuration) fo The following is a reference of available variables via the headers of the invocation message (auto-populated by Cloud Functions), accessible within the container. -For examples of how to extract and use some of these variables, see [NVCF Container Helper Functions](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main). +For examples of how to extract and use some of these variables, see [NVCF Container Helper Functions](https://github.com/NVIDIA/nvcf/tree/main/src/libraries/python/nv-cloud-function-helpers). | Name | Description | | ---------------------------- | ------------------------------------------------------- | diff --git a/docs/v0.6.0/grpc-load-testing.md b/docs/v0.6.0/grpc-load-testing.md index c78c344f1..785e7a517 100644 --- a/docs/v0.6.0/grpc-load-testing.md +++ b/docs/v0.6.0/grpc-load-testing.md @@ -37,13 +37,13 @@ The `grpc_echo_sample` from the same repository shares the The source, build instructions, and registry push examples are in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/load_tester_supreme) +[NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/load-tester-supreme) repository. Build and push the image to whichever container registry your cluster has credentials for: ```bash -git clone https://github.com/NVIDIA/nv-cloud-function-helpers.git -cd nv-cloud-function-helpers/examples/function_samples/load_tester_supreme +git clone https://github.com/NVIDIA/nvcf.git +cd nvcf/examples/function-samples/load-tester-supreme # Build docker build --platform linux/amd64 -t load_tester_supreme . @@ -115,8 +115,8 @@ The CLI saves the function and version IDs automatically. Run ## Clone the load test scripts ```bash -git clone https://github.com/NVIDIA/nv-cloud-function-helpers.git -cd nv-cloud-function-helpers/examples/load-tests +git clone https://github.com/NVIDIA/nvcf.git +cd nvcf/examples/load-tests ``` ## Install k6 diff --git a/docs/v0.6.0/helm-functions.md b/docs/v0.6.0/helm-functions.md index 509f8f64b..ecd2b748a 100644 --- a/docs/v0.6.0/helm-functions.md +++ b/docs/v0.6.0/helm-functions.md @@ -41,7 +41,7 @@ All Pod specs in your helm chart will be updated with pull secrets at runtime, s **Example Creation via API** -Please see our [sample helm chart used](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/helmchart_samples/inference_test_sample) in this example for reference. +Please see our [sample helm chart used](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/helmchart-samples/inference-test-sample) in this example for reference. Below is an example function creation API call creating a helm-based function: @@ -72,7 +72,7 @@ For gRPC-based functions, set `"inferenceURL" : "/gRPC"`. This signals to Cloud To create a multi-node helm deployment, you need to use the following format for the `instanceType`: `.GPU._x[.x]`. For example, `DGXC.GPU.L40S_1x` is a single L40S instance while `ON-PREM.GPU.B200_8x.x2` is two full nodes of 8-way B200. -A sample helm chart for a multi-node deployment can be found [in the multi-node helm example](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/helmchart_samples/multi_node_helm_function_test/). +A sample helm chart for a multi-node deployment can be found [in the multi-node helm example](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/helmchart-samples/multi-node-helm-function-test/). ## Limitations diff --git a/docs/v0.6.0/helmfile-installation.md b/docs/v0.6.0/helmfile-installation.md index 0bfc1c321..3063d3661 100644 --- a/docs/v0.6.0/helmfile-installation.md +++ b/docs/v0.6.0/helmfile-installation.md @@ -191,7 +191,7 @@ Environment configuration files define how NVCF is deployed in your specific env Set `HELMFILE_ENV` to your environment name and copy the base configuration. The filename must match `HELMFILE_ENV` because Helmfile uses it to select the environment file. The template below shows the values to configure for Amazon -EKS ([cp-env-eks-example.yaml](samples/configs/cp-env-eks-example.yaml)). +EKS ([cp-env-eks-example.yaml](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.6.0/samples/configs/cp-env-eks-example.yaml)). ```bash cd path/to/nvcf-self-managed-stack @@ -586,7 +586,7 @@ These credentials will then be used for function deployments. Note that if the r Copy the secrets template using the same `HELMFILE_ENV` value from Step 2. The filename must match `HELMFILE_ENV` because Helmfile loads the corresponding secrets file. The example below shows the required structure -([example-secrets.yaml](samples/configs/cp-example-secrets.yaml)). You must +([example-secrets.yaml](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.6.0/samples/configs/cp-example-secrets.yaml)). You must replace all instances of `REPLACE_WITH_BASE64_DOCKER_CREDENTIAL` with your actual base64-encoded registry credentials. @@ -731,7 +731,7 @@ registry. If your `image` registry is private and your cluster nodes do not have built-in credential helpers, you must create Kubernetes `docker-registry` secrets in each NVCF namespace and configure the helmfile to reference them. 1. Create the pull secret in each NVCF namespace - ([create-nvcr-pull-secrets.sh](samples/scripts/create-nvcr-pull-secrets.sh)): + ([create-nvcr-pull-secrets.sh](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.6.0/samples/scripts/create-nvcr-pull-secrets.sh)): ```bash export NGC_API_KEY="" diff --git a/docs/v0.6.0/http-load-testing.md b/docs/v0.6.0/http-load-testing.md index 981ada37b..465fa6965 100644 --- a/docs/v0.6.0/http-load-testing.md +++ b/docs/v0.6.0/http-load-testing.md @@ -29,13 +29,13 @@ for high-throughput benchmarking and includes: - Built-in OpenTelemetry tracing The source, build instructions, and registry push examples are in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/load_tester_supreme) +[NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/load-tester-supreme) repository. Build and push the image to whichever container registry your cluster has credentials for: ```bash -git clone https://github.com/NVIDIA/nv-cloud-function-helpers.git -cd nv-cloud-function-helpers/examples/function_samples/load_tester_supreme +git clone https://github.com/NVIDIA/nvcf.git +cd nvcf/examples/function-samples/load-tester-supreme # Build docker build --platform linux/amd64 -t load_tester_supreme . @@ -100,8 +100,8 @@ k3d, Docker Desktop) it is typically `localhost` or `127.0.0.1`. ## Clone the load test scripts ```bash -git clone https://github.com/NVIDIA/nv-cloud-function-helpers.git -cd nv-cloud-function-helpers/examples/load-tests +git clone https://github.com/NVIDIA/nvcf.git +cd nvcf/examples/load-tests ``` ## Install k6 diff --git a/docs/v0.6.0/http-soak-testing.md b/docs/v0.6.0/http-soak-testing.md index 061e08ebd..dbd1cec8f 100644 --- a/docs/v0.6.0/http-soak-testing.md +++ b/docs/v0.6.0/http-soak-testing.md @@ -32,13 +32,13 @@ for high-throughput benchmarking and includes: - Built-in OpenTelemetry tracing The source, build instructions, and registry push examples are in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers/tree/main/examples/function_samples/load_tester_supreme) +[NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples/function-samples/load-tester-supreme) repository. Build and push the image to whichever container registry your cluster has credentials for: ```bash -git clone https://github.com/NVIDIA/nv-cloud-function-helpers.git -cd nv-cloud-function-helpers/examples/function_samples/load_tester_supreme +git clone https://github.com/NVIDIA/nvcf.git +cd nvcf/examples/function-samples/load-tester-supreme # Build (multi-arch) docker buildx build --platform linux/amd64,linux/arm64 -t load_tester_supreme . @@ -159,7 +159,7 @@ you want a steady, predictable load. The latest version of this script is maintained in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers) +[NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples) repository. diff --git a/docs/v0.6.0/observability.md b/docs/v0.6.0/observability.md index 8d8150ba5..0a6520801 100644 --- a/docs/v0.6.0/observability.md +++ b/docs/v0.6.0/observability.md @@ -295,7 +295,7 @@ Dashboards are provided in native Grafana JSON format for [file-provisioning](ht Load dashboards into Grafana by placing them in `/etc/grafana/provisioning/dashboards/` on startup. Published dashboards will be available in the -[nv-cloud-function-helpers](https://github.com/NVIDIA/nv-cloud-function-helpers) public GitHub repository. +[NVCF examples](https://github.com/NVIDIA/nvcf/tree/main/examples) public GitHub repository. ## Troubleshooting diff --git a/docs/v0.6.0/troubleshooting.md b/docs/v0.6.0/troubleshooting.md index e57f5a064..8e8763f72 100644 --- a/docs/v0.6.0/troubleshooting.md +++ b/docs/v0.6.0/troubleshooting.md @@ -1050,7 +1050,7 @@ echo "==============================================" ``` -[force-cleanup-nvcf.sh](samples/scripts/force-cleanup-nvcf.sh) +[force-cleanup-nvcf.sh](https://raw.githubusercontent.com/NVIDIA/nvcf/main/docs/v0.6.0/samples/scripts/force-cleanup-nvcf.sh) **Usage:**