Skip to content

GitLab

"lib/runtime/src/vscode:/vscode.git/clone" did not exist on "382a26f0ab7c53eb74f5f4ee6827521d5afa8a66"
Unverified Commit fcdf6610 authored by Julien Mancuso's avatar Julien Mancuso Committed by GitHub
Browse files

chore: document all env vars injected by operator (#6548) 


Signed-off-by: default avatarJulien Mancuso <jmancuso@nvidia.com>
parent 4ea80e95
Show whitespace changes
Inline Side-by-side
Showing with 186 additions and 40 deletions
deploy/operator/docs/footer.md
View file @ fcdf6610
...@@ -167,42 +167,98 @@ The operator automatically selects between two deployment modes based on paralle ...@@ -167,42 +167,98 @@ The operator automatically selects between two deployment modes based on paralle
## Environment Variables ## Environment Variables
The operator automatically injects environment variables based on component type and configuration: The operator automatically injects environment variables into component containers based on component type, backend framework, and operator configuration. User-provided `envs` values always take precedence over operator defaults.
### All Components ### All Components
- **`DYN_NAMESPACE`**: The Dynamo namespace for the component These environment variables are injected into every component container regardless of type.
- **`DYN_PARENT_DGD_K8S_NAME`**: The parent DynamoGraphDeployment Kubernetes resource name
- **`DYN_PARENT_DGD_K8S_NAMESPACE`**: The parent DynamoGraphDeployment Kubernetes namespace | Variable | Purpose | Default | Type | Source |
| --- | --- | --- | --- | --- |
| `DYN_NAMESPACE` | Dynamo service namespace used for service discovery and routing | Derived from DGD spec | `string` | Downward API annotation on checkpoint-restored pods |
| `DYN_COMPONENT` | Identifies the component type for runtime behavior | One of: `frontend`, `worker`, `prefill`, `decode`, `planner`, `epp` | `string` | Set from component spec |
| `DYN_PARENT_DGD_K8S_NAME` | Kubernetes name of the parent DynamoGraphDeployment resource | — | `string` | Set from DGD metadata |
| `DYN_PARENT_DGD_K8S_NAMESPACE` | Kubernetes namespace of the parent DynamoGraphDeployment resource | — | `string` | Set from DGD metadata |
| `POD_NAME` | Current pod name | — | `string` | Downward API (`metadata.name`) |
| `POD_NAMESPACE` | Current pod namespace | — | `string` | Downward API (`metadata.namespace`) |
| `POD_UID` | Current pod UID | — | `string` | Downward API (`metadata.uid`) |
| `DYN_DISCOVERY_BACKEND` | Service discovery backend for inter-component communication | `kubernetes` | `string` | Options: `kubernetes`, `etcd` |
### Infrastructure (Conditional)
These are injected into all components when the corresponding infrastructure service is configured in the operator's `OperatorConfiguration`.
| Variable | Purpose | Default | Type | Condition |
| --- | --- | --- | --- | --- |
| `NATS_SERVER` | NATS messaging server address | — | `string` | Set when `infrastructure.natsAddress` is configured |
| `ETCD_ENDPOINTS` | etcd endpoint addresses for distributed state | — | `string` | Set when `infrastructure.etcdAddress` is configured |
| `MODEL_EXPRESS_URL` | Model Express service URL for model management | — | `string` | Set when `infrastructure.modelExpressURL` is configured |
| `PROMETHEUS_ENDPOINT` | Prometheus endpoint for metrics collection | — | `string` | Set when `infrastructure.prometheusEndpoint` is configured |
### Frontend Components ### Frontend Components
- **`DYNAMO_PORT`**: `8000` | Variable | Purpose | Default | Type |
- **`DYN_HTTP_PORT`**: `8000` | --- | --- | --- | --- |
| `DYNAMO_PORT` | HTTP port the frontend listens on | `8000` | `int` |
| `DYN_HTTP_PORT` | HTTP port for the frontend service (alias) | `8000` | `int` |
| `DYN_NAMESPACE_PREFIX` | Namespace prefix used for frontend request routing | Same as `DYN_NAMESPACE` | `string` |
### Worker Components ### Worker Components
- **`DYN_SYSTEM_PORT`**: `9090` (automatically enables the system metrics server) | Variable | Purpose | Default | Type |
- **`DYN_SYSTEM_USE_ENDPOINT_HEALTH_STATUS`**: `["generate"]` | --- | --- | --- | --- |
- **`DYN_SYSTEM_ENABLED`**: `true` (needed for runtime images 0.6.1 and older) | `DYN_SYSTEM_ENABLED` | Enables the system HTTP server for health checks and metrics | `true` | `string` (boolean) |
- **`NIXL_TELEMETRY_PROMETHEUS_PORT`**: `19090` | `DYN_SYSTEM_USE_ENDPOINT_HEALTH_STATUS` | Endpoints whose health status is used for readiness | `["generate"]` | `string` (JSON array) |
- **`NIXL_TELEMETRY_EXPORTER`**: `prometheus` | `DYN_SYSTEM_PORT` | Port for the system HTTP server (health, metrics) | `9090` | `int` |
- **`NIXL_TELEMETRY_ENABLE`**: `n` (by default NIXL telemetry is disabled) | `DYN_HEALTH_CHECK_ENABLED` | Disables the legacy health check mechanism in favor of the system server | `false` | `string` (boolean) |
| `NIXL_TELEMETRY_ENABLE` | Enables or disables NIXL telemetry collection | `n` | `string` | Options: `y`, `n` |
| `NIXL_TELEMETRY_EXPORTER` | Telemetry exporter format for NIXL metrics | `prometheus` | `string` |
| `NIXL_TELEMETRY_PROMETHEUS_PORT` | Port for NIXL Prometheus metrics endpoint | `19090` | `int` |
| `DYN_NAMESPACE_WORKER_SUFFIX` | Hash suffix appended to worker namespace for rolling updates | — | `string` | Only set during rolling update transitions |
### Planner Components ### Planner Components
- **`PLANNER_PROMETHEUS_PORT`**: `9085` | Variable | Purpose | Default | Type |
| --- | --- | --- | --- |
| `PLANNER_PROMETHEUS_PORT` | Port for the planner's Prometheus metrics endpoint | `9085` | `int` |
### EPP (Endpoint Picker Plugin) Components
| Variable | Purpose | Default | Type |
| --- | --- | --- | --- |
| `USE_STREAMING` | Enables streaming mode for inference request proxying | `true` | `string` (boolean) |
| `RUST_LOG` | Rust log level and filter configuration | `debug,dynamo_llm::kv_router=trace` | `string` |
### VLLM Backend
| Variable | Purpose | Default | Type | Condition |
| --- | --- | --- | --- | --- |
| `VLLM_CACHE_ROOT` | Directory for vLLM compilation cache artifacts | — | `string` | Set when a volume mount has `useAsCompilationCache: true` |
| `VLLM_NIXL_SIDE_CHANNEL_HOST` | Host IP for the NIXL side channel in multiprocessing mode | Pod IP | `string` | Multinode mp backend only (Downward API: `status.podIP`) |
### TensorRT-LLM Backend
### VLLM Backend (with compilation cache) | Variable | Purpose | Default | Type | Condition |
| --- | --- | --- | --- | --- |
| `OMPI_MCA_orte_keep_fqdn_hostnames` | Instructs OpenMPI to preserve FQDN hostnames for inter-node communication | `1` | `string` | Multinode deployments only |
When a volume mount is configured with `useAsCompilationCache: true`: ### Checkpoint / Restore
- **`VLLM_CACHE_ROOT`**: Set to the mount point of the cache volume
## Service Account These environment variables are injected when checkpoint/restore is enabled for a component.
Planner components automatically receive the following service account: | Variable | Purpose | Default | Type | Condition |
| --- | --- | --- | --- | --- |
| `DYN_CHECKPOINT_PATH` | Base directory where checkpoint data is stored | From operator checkpoint config `storage.pvc.basePath` | `string` | PVC storage type |
| `DYN_CHECKPOINT_LOCATION` | Full checkpoint URI (for non-PVC backends) | — | `string` | S3 or OCI storage type |
| `DYN_CHECKPOINT_HASH` | Identity hash that uniquely identifies the checkpoint | — | `string` | Always set when checkpoint is enabled |
| `SKIP_WAIT_FOR_CHECKPOINT` | Skips the checkpoint readiness polling loop; checks once and proceeds | — | `string` | Set on restored and DGD pods |
- **`serviceAccountName`**: `planner-serviceaccount` ## Service Accounts
The following component types automatically receive dedicated service accounts:
- **Planner**: `planner-serviceaccount`
- **EPP**: `epp-serviceaccount`
## Image Pull Secrets ## Image Pull Secrets
...@@ -239,15 +295,29 @@ Default container ports are configured based on component type: ...@@ -239,15 +295,29 @@ Default container ports are configured based on component type:
- **Name**: `http` - **Name**: `http`
### Worker Components ### Worker Components
- **Port**: 9090 - **Port**: 9090 (system)
- **Protocol**: TCP - **Protocol**: TCP
- **Name**: `system` - **Name**: `system`
- **Port**: 19090 (NIXL)
- **Protocol**: TCP
- **Name**: `nixl`
### Planner Components ### Planner Components
- **Port**: 9085 - **Port**: 9085
- **Protocol**: TCP - **Protocol**: TCP
- **Name**: `metrics` - **Name**: `metrics`
### EPP Components
- **Port**: 9002 (gRPC)
- **Protocol**: TCP
- **Name**: `grpc`
- **Port**: 9003 (gRPC health)
- **Protocol**: TCP
- **Name**: `grpc-health`
- **Port**: 9090 (metrics)
- **Protocol**: TCP
- **Name**: `metrics`
## Backend-Specific Configurations ## Backend-Specific Configurations
### VLLM ### VLLM
...@@ -267,14 +337,17 @@ For users who want to understand the implementation details or contribute to the ...@@ -267,14 +337,17 @@ For users who want to understand the implementation details or contribute to the
- **Health Probes, Security Context & Pod Specifications**: [`internal/dynamo/graph.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/graph.go) - Contains the main logic for applying default probes, security context, environment variables, shared memory, and pod configurations - **Health Probes, Security Context & Pod Specifications**: [`internal/dynamo/graph.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/graph.go) - Contains the main logic for applying default probes, security context, environment variables, shared memory, and pod configurations
- **Component-Specific Defaults**: - **Component-Specific Defaults**:
- [`internal/dynamo/component_common.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_common.go) - Base container and pod spec shared by all component types
- [`internal/dynamo/component_frontend.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_frontend.go) - [`internal/dynamo/component_frontend.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_frontend.go)
- [`internal/dynamo/component_worker.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_worker.go) - [`internal/dynamo/component_worker.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_worker.go)
- [`internal/dynamo/component_planner.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_planner.go) - [`internal/dynamo/component_planner.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_planner.go)
- [`internal/dynamo/component_epp.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_epp.go)
- **Image Pull Secrets**: [`internal/secrets/docker.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/secrets/docker.go) - Implements the docker secret indexer and automatic discovery - **Image Pull Secrets**: [`internal/secrets/docker.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/secrets/docker.go) - Implements the docker secret indexer and automatic discovery
- **Backend-Specific Behavior**: - **Backend-Specific Behavior**:
- [`internal/dynamo/backend_vllm.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/backend_vllm.go) - [`internal/dynamo/backend_vllm.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/backend_vllm.go)
- [`internal/dynamo/backend_sglang.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/backend_sglang.go) - [`internal/dynamo/backend_sglang.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/backend_sglang.go)
- [`internal/dynamo/backend_trtllm.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/backend_trtllm.go) - [`internal/dynamo/backend_trtllm.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/backend_trtllm.go)
- **Checkpoint / Restore**: [`internal/checkpoint/dgd_integration.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/checkpoint/dgd_integration.go) - Checkpoint env var injection and volume setup
- **Constants & Annotations**: [`internal/consts/consts.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/consts/consts.go) - Defines annotation keys and other constants - **Constants & Annotations**: [`internal/consts/consts.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/consts/consts.go) - Defines annotation keys and other constants
## Notes ## Notes
......
docs/pages/kubernetes/api-reference.md
View file @ fcdf6610
...@@ -2228,42 +2228,98 @@ The operator automatically selects between two deployment modes based on paralle ...@@ -2228,42 +2228,98 @@ The operator automatically selects between two deployment modes based on paralle
## Environment Variables ## Environment Variables
The operator automatically injects environment variables based on component type and configuration: The operator automatically injects environment variables into component containers based on component type, backend framework, and operator configuration. User-provided `envs` values always take precedence over operator defaults.
### All Components ### All Components
- **`DYN_NAMESPACE`**: The Dynamo namespace for the component These environment variables are injected into every component container regardless of type.
- **`DYN_PARENT_DGD_K8S_NAME`**: The parent DynamoGraphDeployment Kubernetes resource name
- **`DYN_PARENT_DGD_K8S_NAMESPACE`**: The parent DynamoGraphDeployment Kubernetes namespace | Variable | Purpose | Default | Type | Source |
| --- | --- | --- | --- | --- |
| `DYN_NAMESPACE` | Dynamo service namespace used for service discovery and routing | Derived from DGD spec | `string` | Downward API annotation on checkpoint-restored pods |
| `DYN_COMPONENT` | Identifies the component type for runtime behavior | One of: `frontend`, `worker`, `prefill`, `decode`, `planner`, `epp` | `string` | Set from component spec |
| `DYN_PARENT_DGD_K8S_NAME` | Kubernetes name of the parent DynamoGraphDeployment resource | — | `string` | Set from DGD metadata |
| `DYN_PARENT_DGD_K8S_NAMESPACE` | Kubernetes namespace of the parent DynamoGraphDeployment resource | — | `string` | Set from DGD metadata |
| `POD_NAME` | Current pod name | — | `string` | Downward API (`metadata.name`) |
| `POD_NAMESPACE` | Current pod namespace | — | `string` | Downward API (`metadata.namespace`) |
| `POD_UID` | Current pod UID | — | `string` | Downward API (`metadata.uid`) |
| `DYN_DISCOVERY_BACKEND` | Service discovery backend for inter-component communication | `kubernetes` | `string` | Options: `kubernetes`, `etcd` |
### Infrastructure (Conditional)
These are injected into all components when the corresponding infrastructure service is configured in the operator's `OperatorConfiguration`.
| Variable | Purpose | Default | Type | Condition |
| --- | --- | --- | --- | --- |
| `NATS_SERVER` | NATS messaging server address | — | `string` | Set when `infrastructure.natsAddress` is configured |
| `ETCD_ENDPOINTS` | etcd endpoint addresses for distributed state | — | `string` | Set when `infrastructure.etcdAddress` is configured |
| `MODEL_EXPRESS_URL` | Model Express service URL for model management | — | `string` | Set when `infrastructure.modelExpressURL` is configured |
| `PROMETHEUS_ENDPOINT` | Prometheus endpoint for metrics collection | — | `string` | Set when `infrastructure.prometheusEndpoint` is configured |
### Frontend Components ### Frontend Components
- **`DYNAMO_PORT`**: `8000` | Variable | Purpose | Default | Type |
- **`DYN_HTTP_PORT`**: `8000` | --- | --- | --- | --- |
| `DYNAMO_PORT` | HTTP port the frontend listens on | `8000` | `int` |
| `DYN_HTTP_PORT` | HTTP port for the frontend service (alias) | `8000` | `int` |
| `DYN_NAMESPACE_PREFIX` | Namespace prefix used for frontend request routing | Same as `DYN_NAMESPACE` | `string` |
### Worker Components ### Worker Components
- **`DYN_SYSTEM_PORT`**: `9090` (automatically enables the system metrics server) | Variable | Purpose | Default | Type |
- **`DYN_SYSTEM_USE_ENDPOINT_HEALTH_STATUS`**: `["generate"]` | --- | --- | --- | --- |
- **`DYN_SYSTEM_ENABLED`**: `true` (needed for runtime images 0.6.1 and older) | `DYN_SYSTEM_ENABLED` | Enables the system HTTP server for health checks and metrics | `true` | `string` (boolean) |
- **`NIXL_TELEMETRY_PROMETHEUS_PORT`**: `19090` | `DYN_SYSTEM_USE_ENDPOINT_HEALTH_STATUS` | Endpoints whose health status is used for readiness | `["generate"]` | `string` (JSON array) |
- **`NIXL_TELEMETRY_EXPORTER`**: `prometheus` | `DYN_SYSTEM_PORT` | Port for the system HTTP server (health, metrics) | `9090` | `int` |
- **`NIXL_TELEMETRY_ENABLE`**: `n` (by default NIXL telemetry is disabled) | `DYN_HEALTH_CHECK_ENABLED` | Disables the legacy health check mechanism in favor of the system server | `false` | `string` (boolean) |
| `NIXL_TELEMETRY_ENABLE` | Enables or disables NIXL telemetry collection | `n` | `string` | Options: `y`, `n` |
| `NIXL_TELEMETRY_EXPORTER` | Telemetry exporter format for NIXL metrics | `prometheus` | `string` |
| `NIXL_TELEMETRY_PROMETHEUS_PORT` | Port for NIXL Prometheus metrics endpoint | `19090` | `int` |
| `DYN_NAMESPACE_WORKER_SUFFIX` | Hash suffix appended to worker namespace for rolling updates | — | `string` | Only set during rolling update transitions |
### Planner Components ### Planner Components
- **`PLANNER_PROMETHEUS_PORT`**: `9085` | Variable | Purpose | Default | Type |
| --- | --- | --- | --- |
| `PLANNER_PROMETHEUS_PORT` | Port for the planner's Prometheus metrics endpoint | `9085` | `int` |
### EPP (Endpoint Picker Plugin) Components
| Variable | Purpose | Default | Type |
| --- | --- | --- | --- |
| `USE_STREAMING` | Enables streaming mode for inference request proxying | `true` | `string` (boolean) |
| `RUST_LOG` | Rust log level and filter configuration | `debug,dynamo_llm::kv_router=trace` | `string` |
### VLLM Backend
### VLLM Backend (with compilation cache) | Variable | Purpose | Default | Type | Condition |
| --- | --- | --- | --- | --- |
| `VLLM_CACHE_ROOT` | Directory for vLLM compilation cache artifacts | — | `string` | Set when a volume mount has `useAsCompilationCache: true` |
| `VLLM_NIXL_SIDE_CHANNEL_HOST` | Host IP for the NIXL side channel in multiprocessing mode | Pod IP | `string` | Multinode mp backend only (Downward API: `status.podIP`) |
When a volume mount is configured with `useAsCompilationCache: true`: ### TensorRT-LLM Backend
- **`VLLM_CACHE_ROOT`**: Set to the mount point of the cache volume
## Service Account | Variable | Purpose | Default | Type | Condition |
| --- | --- | --- | --- | --- |
| `OMPI_MCA_orte_keep_fqdn_hostnames` | Instructs OpenMPI to preserve FQDN hostnames for inter-node communication | `1` | `string` | Multinode deployments only |
Planner components automatically receive the following service account: ### Checkpoint / Restore
- **`serviceAccountName`**: `planner-serviceaccount` These environment variables are injected when checkpoint/restore is enabled for a component.
| Variable | Purpose | Default | Type | Condition |
| --- | --- | --- | --- | --- |
| `DYN_CHECKPOINT_PATH` | Base directory where checkpoint data is stored | From operator checkpoint config `storage.pvc.basePath` | `string` | PVC storage type |
| `DYN_CHECKPOINT_LOCATION` | Full checkpoint URI (for non-PVC backends) | — | `string` | S3 or OCI storage type |
| `DYN_CHECKPOINT_HASH` | Identity hash that uniquely identifies the checkpoint | — | `string` | Always set when checkpoint is enabled |
| `SKIP_WAIT_FOR_CHECKPOINT` | Skips the checkpoint readiness polling loop; checks once and proceeds | — | `string` | Set on restored and DGD pods |
## Service Accounts
The following component types automatically receive dedicated service accounts:
- **Planner**: `planner-serviceaccount`
- **EPP**: `epp-serviceaccount`
## Image Pull Secrets ## Image Pull Secrets
...@@ -2300,15 +2356,29 @@ Default container ports are configured based on component type: ...@@ -2300,15 +2356,29 @@ Default container ports are configured based on component type:
- **Name**: `http` - **Name**: `http`
### Worker Components ### Worker Components
- **Port**: 9090 - **Port**: 9090 (system)
- **Protocol**: TCP - **Protocol**: TCP
- **Name**: `system` - **Name**: `system`
- **Port**: 19090 (NIXL)
- **Protocol**: TCP
- **Name**: `nixl`
### Planner Components ### Planner Components
- **Port**: 9085 - **Port**: 9085
- **Protocol**: TCP - **Protocol**: TCP
- **Name**: `metrics` - **Name**: `metrics`
### EPP Components
- **Port**: 9002 (gRPC)
- **Protocol**: TCP
- **Name**: `grpc`
- **Port**: 9003 (gRPC health)
- **Protocol**: TCP
- **Name**: `grpc-health`
- **Port**: 9090 (metrics)
- **Protocol**: TCP
- **Name**: `metrics`
## Backend-Specific Configurations ## Backend-Specific Configurations
### VLLM ### VLLM
...@@ -2328,14 +2398,17 @@ For users who want to understand the implementation details or contribute to the ...@@ -2328,14 +2398,17 @@ For users who want to understand the implementation details or contribute to the
- **Health Probes, Security Context & Pod Specifications**: [`internal/dynamo/graph.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/graph.go) - Contains the main logic for applying default probes, security context, environment variables, shared memory, and pod configurations - **Health Probes, Security Context & Pod Specifications**: [`internal/dynamo/graph.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/graph.go) - Contains the main logic for applying default probes, security context, environment variables, shared memory, and pod configurations
- **Component-Specific Defaults**: - **Component-Specific Defaults**:
- [`internal/dynamo/component_common.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_common.go) - Base container and pod spec shared by all component types
- [`internal/dynamo/component_frontend.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_frontend.go) - [`internal/dynamo/component_frontend.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_frontend.go)
- [`internal/dynamo/component_worker.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_worker.go) - [`internal/dynamo/component_worker.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_worker.go)
- [`internal/dynamo/component_planner.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_planner.go) - [`internal/dynamo/component_planner.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_planner.go)
- [`internal/dynamo/component_epp.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/component_epp.go)
- **Image Pull Secrets**: [`internal/secrets/docker.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/secrets/docker.go) - Implements the docker secret indexer and automatic discovery - **Image Pull Secrets**: [`internal/secrets/docker.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/secrets/docker.go) - Implements the docker secret indexer and automatic discovery
- **Backend-Specific Behavior**: - **Backend-Specific Behavior**:
- [`internal/dynamo/backend_vllm.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/backend_vllm.go) - [`internal/dynamo/backend_vllm.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/backend_vllm.go)
- [`internal/dynamo/backend_sglang.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/backend_sglang.go) - [`internal/dynamo/backend_sglang.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/backend_sglang.go)
- [`internal/dynamo/backend_trtllm.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/backend_trtllm.go) - [`internal/dynamo/backend_trtllm.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/dynamo/backend_trtllm.go)
- **Checkpoint / Restore**: [`internal/checkpoint/dgd_integration.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/checkpoint/dgd_integration.go) - Checkpoint env var injection and volume setup
- **Constants & Annotations**: [`internal/consts/consts.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/consts/consts.go) - Defines annotation keys and other constants - **Constants & Annotations**: [`internal/consts/consts.go`](https://github.com/ai-dynamo/dynamo/blob/main/deploy/operator/internal/consts/consts.go) - Defines annotation keys and other constants
## Notes ## Notes
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment