Default Spectrum-X settings from GPU platform

README.md

@@ -31,6 +31,17 @@ Discovery fills missing profile values from hardware and built-in defaults.
 Values already present under `profile` are preserved, while explicit CLI flags
 (`--fabric`, `--deployment-type`, `--multirail`, `--routing`, `--ignore-arp`,
 `--spectrum-x`) take precedence.
+
+For Spectrum-X, discovery combines the east-west NIC device ID with each
+group's `gpuType` (or `machineType` fallback). H100/H200/B200/GB200 platforms
+default to `multiplaneMode: none` and `numberOfPlanes: 1`. B300 and GB300
+default to the common GA dual-plane configuration, `swplb` with 2 planes.
+Platform type cannot distinguish `swplb` from `hwplb`: both are available on
+B300 and GB300, while `hwplb` is an explicit opt-in. Pass
+`--multiplane-mode hwplb` when required, and pass `--number-of-planes 4`
+explicitly for a quad-plane B300 topology. The same defaults apply when
+`--for` supplies hardware from a topology preset.
+
 AI-driven profile selection now lives in the `k8s-launch-kit-*` Claude Code
 skills, which wrap the deterministic CLI commands.
 

docs/reference/cli.md

@@ -68,8 +68,8 @@ Discovery also accepts the profile and Spectrum-X flags below. Explicit flags ov
 | Flag | Description |
 | --- | --- |
 | `--spectrum-x` | Enable Spectrum-X and select RA version, such as `RA2.3`. |
-| `--multiplane-mode` | `none`, `swplb`, or `hwplb`. |
-| `--number-of-planes` | Plane count for Spectrum-X. |
+| `--multiplane-mode` | `none`, `swplb`, or `hwplb`. Defaults from GPU platform and east-west NIC: single-plane H100/H200/B200/GB200 use `none`; B300/GB300 use the GA `swplb` default. Select `hwplb` explicitly. |
+| `--number-of-planes` | Plane count for Spectrum-X. Defaults to 1 for single-plane platforms and 2 for B300/GB300; pass 4 explicitly for quad-plane B300. |
 | `--topology-scheme` | `2-tier` or `3-tier` for topology-driven CIDRPool allocation. |
 | `--ip-version` | `ipv4` for per-node `/31` allocation or `ipv6` for per-node `/64` allocation. |
 | `--topology-file` | Path to spcx-gen/reference-generator or contract-compliant NVIDIA AIR topology JSON. The format is detected from its structure. |

docs/reference/configuration.md

@@ -264,8 +264,8 @@ profile:
 | `ignoreARP` | Adds per-interface ARP tuning outside Spectrum-X. |
 | `spectrumX.enable` | Select a Spectrum-X profile. |
 | `spectrumX.spcxVersion` | `RA2.1`, `RA2.2`, or `RA2.3`. |
-| `spectrumX.multiplaneMode` | `none`, `swplb`, or `hwplb`. |
-| `spectrumX.numberOfPlanes` | `1`, `2`, or `4`. |
+| `spectrumX.multiplaneMode` | `none`, `swplb`, or `hwplb`. When absent, H100/H200/B200/GB200 default to `none`; B300/GB300 default to the GA `swplb` path. Platform type cannot distinguish `swplb` from `hwplb`, so `hwplb` must be selected explicitly. |
+| `spectrumX.numberOfPlanes` | `1`, `2`, or `4`. Single-plane platforms default to 1; B300/GB300 default to 2. Pass 4 explicitly for quad-plane B300. |
 | `spectrumX.topologyType` | `2-tier` or `3-tier`. |
 | `spectrumX.ipVersion` | `ipv4` for per-node `/31` allocation or `ipv6` for per-node `/64` allocation. |
 | `spectrumX.hostFirstOctet` | Config-only first octet for generated IPv4 topology addressing. |

docs/user/spectrum-x.md

@@ -35,6 +35,27 @@ l8k generate \
 | `swplb` | Software plane load balancing. Renders per-rail, per-plane resources. |
 | `hwplb` | Hardware plane load balancing for larger topologies. |
 
+### Platform-derived defaults
+
+When `multiplaneMode` or `numberOfPlanes` is absent, l8k combines the
+discovered GPU platform with the east-west NIC device ID:
+
+| GPU platform | Default mode | Default planes | Notes |
+| --- | --- | --- | --- |
+| H100, H200, B200, GB200 | `none` | 1 | Single-plane architecture. |
+| B300 | `swplb` | 2 | Conservative dual-plane default; pass 4 explicitly for a quad-plane topology. |
+| GB300 | `swplb` | 2 | Dual-plane architecture. |
+
+The platform is read from `clusterConfig[].gpuType`, with `machineType` as a
+fallback. `--for` presets participate in the same resolution before manifests
+are rendered.
+
+B300 and GB300 support both `swplb` and `hwplb`, so platform type does not
+identify which load-balancing mechanism the fabric uses. l8k defaults to the
+documented GA `swplb` path. Select `hwplb` explicitly when the site topology
+requires hardware plane load balancing. Explicit config values and CLI flags
+always override these defaults.
+
 ```bash
 l8k discover \
   --spectrum-x RA2.3 \

pkg/app/generate.go

@@ -74,6 +74,36 @@ func (l *Launcher) executeGeneration(configPath string) error {
 		}
 	}
 
+	// --for supplies the hardware inventory used by profile defaulting as well
+	// as rendering. Substitute it before resolveProfileSettings so defaults can
+	// use the preset's machine/gpu types and east-west NICs. Keep the source
+	// inventory separately: generated preset hardware is transient and must not
+	// replace clusterConfig in a file-backed user configuration.
+	sourceClusterConfig := fullConfig.ClusterConfig
+	presetClusterConfigApplied := false
+	if l.options.ForPreset != "" {
+		preset, err := l.presetCatalog.LoadPresetByDir(l.options.ForPreset)
+		if err != nil {
+			return apperrors.NewValidationError(
+				fmt.Sprintf("invalid --for value %q", l.options.ForPreset),
+				err,
+				"Run 'l8k preset list' to see available presets",
+			)
+		}
+		selectorMap := parseNodeSelector(l.options.NodeSelector)
+		cc, synthErr := presets.SynthesizeClusterConfig(l.options.ForPreset, preset, selectorMap)
+		if synthErr != nil {
+			return apperrors.NewValidationError(
+				fmt.Sprintf("preset %q cannot be used with --for", l.options.ForPreset),
+				synthErr,
+				"Add a 'capabilities.nodes.{sriov,rdma,ib}' block to the preset's topology.yaml",
+			)
+		}
+		fullConfig.ClusterConfig = []config.ClusterConfig{cc}
+		presetClusterConfigApplied = true
+		l.ui.Info("Using preset %q (clusterConfig replaced from preset)", l.options.ForPreset)
+	}
+
 	// Resolve the same defaults/config/CLI precedence that discovery uses
 	// before either flow persists or consumes the final profile.
 	if err := l.resolveProfileSettings(fullConfig); err != nil {
@@ -116,39 +146,18 @@ func (l *Launcher) executeGeneration(configPath string) error {
 		)
 	}
 
-	// Persist the exact config used for generation: hardware defaults fill
+	// Persist the exact profile used for generation: hardware defaults fill
 	// missing fields, existing YAML values survive, and explicit CLI options
-	// win. Do this before --for substitutes a synthetic clusterConfig so only
-	// the resolved settings—not preset-only topology—are written back.
-	if err := l.saveResolvedConfig(configPath, fullConfig, srcConfig, srcConfigYAML); err != nil {
-		return err
+	// win. When --for supplied the hardware, restore the source clusterConfig
+	// only in the write-back copy so preset-only topology remains transient.
+	resolvedConfigForWriteBack := fullConfig
+	if presetClusterConfigApplied {
+		writeBackCopy := *fullConfig
+		writeBackCopy.ClusterConfig = sourceClusterConfig
+		resolvedConfigForWriteBack = &writeBackCopy
 	}
-
-	// --for: replace clusterConfig with a synthesized group from a preset.
-	// This is the explicit ahead-of-time generation path that skips live
-	// discovery in favor of a static preset description. The CLI layer has
-	// already enforced --node-selector being set; here we do the substitution
-	// before the rest of the pipeline runs.
-	if l.options.ForPreset != "" {
-		preset, err := l.presetCatalog.LoadPresetByDir(l.options.ForPreset)
-		if err != nil {
-			return apperrors.NewValidationError(
-				fmt.Sprintf("invalid --for value %q", l.options.ForPreset),
-				err,
-				"Run 'l8k preset list' to see available presets",
-			)
-		}
-		selectorMap := parseNodeSelector(l.options.NodeSelector)
-		cc, synthErr := presets.SynthesizeClusterConfig(l.options.ForPreset, preset, selectorMap)
-		if synthErr != nil {
-			return apperrors.NewValidationError(
-				fmt.Sprintf("preset %q cannot be used with --for", l.options.ForPreset),
-				synthErr,
-				"Add a 'capabilities.nodes.{sriov,rdma,ib}' block to the preset's topology.yaml",
-			)
-		}
-		fullConfig.ClusterConfig = []config.ClusterConfig{cc}
-		l.ui.Info("Using preset %q (clusterConfig replaced from preset)", l.options.ForPreset)
+	if err := l.saveResolvedConfig(configPath, resolvedConfigForWriteBack, srcConfig, srcConfigYAML); err != nil {
+		return err
 	}
 
 	aggregatedCapabilities := config.AggregateCapabilities(fullConfig.ClusterConfig)

pkg/app/generate_profile_test.go

@@ -14,6 +14,7 @@ import (
 	"github.com/nvidia/k8s-launch-kit/pkg/config"
 	"github.com/nvidia/k8s-launch-kit/pkg/networkoperatorplugin"
 	"github.com/nvidia/k8s-launch-kit/pkg/options"
+	"github.com/nvidia/k8s-launch-kit/pkg/presets"
 	"github.com/nvidia/k8s-launch-kit/pkg/ui"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
@@ -121,3 +122,48 @@ func TestResolveSpectrumXTopologyFile(t *testing.T) {
 		assert.Equal(t, resolvedCLIPath, cfg.Profile.SpectrumX.ResolvedTopologyFile)
 	})
 }
+
+func TestGenerateUsesPresetHardwareForDefaultsWithoutPersistingPresetInventory(t *testing.T) {
+	configPath := filepath.Join(t.TempDir(), "cluster-config.yaml")
+	source := `networkOperator:
+  selectedRelease: "26.4"
+profile:
+  multirail: true
+  spectrumX:
+    enable: true
+    spcxVersion: RA2.2
+    topologyType: 2-tier
+clusterConfig:
+  - identifier: source-inventory
+    machineType: source-machine
+    gpuType: NVIDIA-H200
+    linkType: Ethernet
+    pfs:
+      - deviceID: a2dc
+        traffic: east-west
+`
+	require.NoError(t, os.WriteFile(configPath, []byte(source), 0o600))
+
+	catalog, err := presets.EmbeddedCatalog()
+	require.NoError(t, err)
+	launcher := New(options.Options{
+		ForPreset:    "GB300-NVL-NVIDIA-GB300",
+		NodeSelector: "nvidia.com/gpu.product=NVIDIA-GB300",
+	})
+	launcher.ui = ui.NewSilent()
+	launcher.presetCatalog = catalog
+
+	require.NoError(t, launcher.executeGeneration(configPath))
+
+	got, err := config.LoadFullConfig(configPath, launcher.logger)
+	require.NoError(t, err)
+	require.NotNil(t, got.Profile)
+	require.NotNil(t, got.Profile.SpectrumX)
+	assert.Equal(t, "swplb", got.Profile.SpectrumX.MultiplaneMode)
+	assert.Equal(t, 2, got.Profile.SpectrumX.NumberOfPlanes)
+	require.Len(t, got.ClusterConfig, 1)
+	assert.Equal(t, "source-inventory", got.ClusterConfig[0].Identifier)
+	assert.Equal(t, "NVIDIA-H200", got.ClusterConfig[0].GPUType)
+	require.Len(t, got.ClusterConfig[0].PFs, 1)
+	assert.Equal(t, "a2dc", got.ClusterConfig[0].PFs[0].DeviceID)
+}

pkg/config/default-config.yaml

@@ -165,8 +165,12 @@ profile:
   spectrumX: # Spectrum-X configuration (set enable: true or use --spectrum-x CLI flag)
     enable: false # CLI parameter (overrides this value): --spectrum-x
     # spcxVersion: "RA2.3" # CLI parameter (overrides this value): --spectrum-x
-    # multiplaneMode: swplb # CLI parameter (overrides this value): --multiplane-mode (none, swplb, hwplb)
-    # numberOfPlanes: 4 # CLI parameter (overrides this value): --number-of-planes, also used as pfsPerNic
+    # CLI override: --multiplane-mode. When absent, H100/H200/B200/GB200 use
+    # none; B300/GB300 use the GA swplb default. Select hwplb explicitly.
+    # multiplaneMode: swplb
+    # CLI override: --number-of-planes, also used as pfsPerNic. Single-plane
+    # platforms use 1; B300/GB300 use 2. Set 4 explicitly for quad-plane B300.
+    # numberOfPlanes: 2
     # topologyType: 2-tier # CLI parameter (overrides this value): --topology-scheme (2-tier, 3-tier)
     # ipVersion: ipv4 # CLI parameter (overrides this value): --ip-version (ipv4 /31 or ipv6 /64 CIDRPool allocation)
     # hostFirstOctet: 172 # Config-only IPv4 first octet override; defaults to 172 for 2-tier, 10 for 3-tier

pkg/options/options.go

@@ -72,8 +72,8 @@ type Options struct {
 	IgnoreARPSet   bool
 	SpectrumX      bool   // True when --spectrum-x is set; derived from SPCXVersion != ""
 	SPCXVersion    string // Spectrum-X RA version (the value of --spectrum-x; empty = disabled)
-	MultiplaneMode string // Spectrum-X multiplane mode (default: swplb)
-	NumberOfPlanes int    // Number of planes for Spectrum-X (default: 4)
+	MultiplaneMode string // Spectrum-X multiplane mode (platform/NIC-derived when empty)
+	NumberOfPlanes int    // Number of planes for Spectrum-X (platform/NIC-derived when zero)
 	TopologyScheme string // Spectrum-X topology scheme: 2-tier or 3-tier
 	IPVersion      string // Spectrum-X address family: ipv4 or ipv6
 	TopologyFile   string // Path to spcx-gen/reference-generator or NVIDIA AIR topology JSON for Spectrum-X CIDRPool generation