feat(inference): add dual DGX Spark express profile

.pre-commit-config.yaml

@@ -167,6 +167,14 @@ repos:
         files: ^(nemoclaw-blueprint/.*\.yaml$|nemoclaw/openclaw\.plugin\.json$|schemas/.*\.json$)
         priority: 10
 
+      - id: validate-managed-inference-catalog
+        name: Validate managed inference catalog
+        entry: npm run catalog:check
+        language: system
+        pass_filenames: false
+        files: ^(managed-inference/(?:presets|recipes)/.*\.yaml$|managed-inference/schemas/.*\.json$|src/lib/inference/serving/(?:adapter-registry|catalog|generate-catalog|types)\.ts$)
+        priority: 10
+
       - id: repository-checks
         name: Repository checks
         entry: npm run checks:repository

ci/platform-matrix.json

@@ -47,7 +47,7 @@
       "status": "tested",
       "prd_priority": "P1",
       "ci_tested": true,
-      "notes": "Use the standard installer and `$$nemoclaw onboard`. For an end-to-end walkthrough with local inference, see the [NVIDIA Spark playbook](https://build.nvidia.com/spark/nemoclaw)."
+      "notes": "Use the standard installer and `$$nemoclaw onboard`. The automatic two-DGX Spark managed-vLLM profile is Experimental, and physical two-node end-to-end validation is pending. For the profile requirements and controls, see [Set Up vLLM on Two DGX Sparks](../inference/local-inference/set-up-vllm-on-two-dgx-sparks). For the validated single-DGX Spark walkthrough with local inference, see the [NVIDIA Spark playbook](https://build.nvidia.com/spark/nemoclaw)."
     },
     {
       "name": "Windows WSL2",

ci/source-architecture-budget.json

@@ -28,7 +28,7 @@
       "src/lib/security/redact.ts": 51,
       "src/lib/state/onboard-session.ts": 36,
       "src/lib/state/registry.ts": 101,
-      "src/lib/state/state-root.ts": 23,
+      "src/lib/state/state-root.ts": 22,
       "src/lib/subprocess-env.ts": 24,
       "src/lib/validation.ts": 25
     }
@@ -46,7 +46,7 @@
       "src/lib/actions/sandbox/snapshot.ts": 39,
       "src/lib/actions/uninstall/run-plan.ts": 25,
       "src/lib/inference/onboard-probes.ts": 21,
-      "src/lib/inference/vllm.ts": 23,
+      "src/lib/inference/vllm.ts": 21,
       "src/lib/onboard.ts": 225,
       "src/lib/onboard/machine/handlers/sandbox.ts": 21,
       "src/lib/sandbox/config.ts": 22,

docs/get-started/prerequisites.mdx

@@ -101,7 +101,7 @@ The table comes from [`ci/platform-matrix.json`](https://github.com/NVIDIA/NemoC
 {/* platform-matrix:begin */}
 | OS | Container runtime | Status | Notes |
 |----|-------------------|--------|-------|
-| DGX OS (Spark) | Docker | Tested | Use the standard installer and `$$nemoclaw onboard`. For an end-to-end walkthrough with local inference, see the [NVIDIA Spark playbook](https://build.nvidia.com/spark/nemoclaw). |
+| DGX OS (Spark) | Docker | Tested | Use the standard installer and `$$nemoclaw onboard`. The automatic two-DGX Spark managed-vLLM profile is Experimental, and physical two-node end-to-end validation is pending. For the profile requirements and controls, see [Set Up vLLM on Two DGX Sparks](../inference/local-inference/set-up-vllm-on-two-dgx-sparks). For the validated single-DGX Spark walkthrough with local inference, see the [NVIDIA Spark playbook](https://build.nvidia.com/spark/nemoclaw). |
 | DGX OS (Station) | Docker | Tested with limitations | Tested with limitations across qualified profiles on one physical DGX Station GB300; see [Additional Setup for DGX Station](additional-setup/dgx-station-preparation) for accepted profiles, the pending no-OTA DGX OS `7.6.x` end-to-end qualification, runtime gates, and current dual-Station and dedicated CI limitations. |
 | Linux | Docker | Tested | Primary tested path. Ubuntu 24.04 has host-level onboarding validation. A digest-pinned Ubuntu 26.04 userspace lane builds the CLI and runs preflight, installer, and platform contracts on eligible main pushes; Docker-host, AppArmor, Landlock, and live onboarding validation on 26.04 remain pending. Other distros (Ubuntu 22.04, Fedora, Rocky, Alma, NixOS, Arch) may work but are not validated. |
 | macOS (Apple Silicon) | Colima, Docker Desktop | Tested with limitations | Start the container runtime (Colima or Docker Desktop) before running the installer. When Homebrew is available, OpenShell uses its official formula and the gateway appears in `brew services list` as `openshell`; without Homebrew, NemoClaw uses the standalone OpenShell install and detached gateway fallback. Homebrew Colima users must install both Colima and the Docker CLI (`brew install colima docker`) before `docker info` can work. Xcode Command Line Tools (`xcode-select --install`) are typically required for Node native modules during install. NemoClaw recommends them but does not enforce them during preflight. |

docs/index.yml

@@ -101,6 +101,9 @@ navigation:
                   - page: "Set Up vLLM"
                     path: _build/agent-variants/inference/set-up-vllm.openclaw.generated.mdx
                     slug: set-up-vllm
+                  - page: "Set Up vLLM on Two DGX Sparks"
+                    path: _build/agent-variants/inference/set-up-vllm-on-two-dgx-sparks.openclaw.generated.mdx
+                    slug: set-up-vllm-on-two-dgx-sparks
                   - page: "Set Up vLLM on Two DGX Stations"
                     path: _build/agent-variants/inference/set-up-vllm-on-two-dgx-stations.openclaw.generated.mdx
                     slug: set-up-vllm-on-two-dgx-stations
@@ -507,6 +510,9 @@ navigation:
                   - page: "Set Up vLLM"
                     path: _build/agent-variants/inference/set-up-vllm.deepagents.generated.mdx
                     slug: set-up-vllm
+                  - page: "Set Up vLLM on Two DGX Sparks"
+                    path: _build/agent-variants/inference/set-up-vllm-on-two-dgx-sparks.deepagents.generated.mdx
+                    slug: set-up-vllm-on-two-dgx-sparks
                   - page: "Set Up vLLM on Two DGX Stations"
                     path: _build/agent-variants/inference/set-up-vllm-on-two-dgx-stations.deepagents.generated.mdx
                     slug: set-up-vllm-on-two-dgx-stations
@@ -835,6 +841,9 @@ navigation:
                   - page: "Set Up vLLM"
                     path: _build/agent-variants/inference/set-up-vllm.hermes.generated.mdx
                     slug: set-up-vllm
+                  - page: "Set Up vLLM on Two DGX Sparks"
+                    path: _build/agent-variants/inference/set-up-vllm-on-two-dgx-sparks.hermes.generated.mdx
+                    slug: set-up-vllm-on-two-dgx-sparks
                   - page: "Set Up vLLM on Two DGX Stations"
                     path: _build/agent-variants/inference/set-up-vllm-on-two-dgx-stations.hermes.generated.mdx
                     slug: set-up-vllm-on-two-dgx-stations