The reference documents a profile's gpu need and its own comfyui block

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

docs/reference.md

@@ -119,6 +119,8 @@ rather than repeated.
 | `name` | `string` | [Federation](#federation) |
 | `interval` | `time.Duration` | [Federation](#federation) |
 | `enabled` | `bool` | [FirewallSettings](#firewallsettings) |
+| `min_compute_capability` | `float64` | [GPUNeed](#gpuneed) |
+| `min_memory_gb` | `int` | [GPUNeed](#gpuneed) |
 | `format` | `string` | [GuardModel](#guardmodel) |
 | `categories` | `[]string` | [GuardModel](#guardmodel) |
 | `name` | `string` | [Input](#input) |
@@ -266,6 +268,9 @@ rather than repeated.
 | `kv_events` | `bool` | [Profile](#profile) |
 | `gpu` | `*GPUNeed` | [Profile](#profile) |
 | `comfyui` | `*ProfileComfyUI` | [Profile](#profile) |
+| `workflow` | `string` | [ProfileComfyUI](#profilecomfyui) |
+| `checkpoint` | `string` | [ProfileComfyUI](#profilecomfyui) |
+| `nodes` | `[]CustomNode` | [ProfileComfyUI](#profilecomfyui) |
 | `activation_wait` | `time.Duration` | [Router](#router) |
 | `scrape_interval` | `time.Duration` | [Router](#router) |
 | `scrape_timeout` | `time.Duration` | [Router](#router) |
@@ -1202,6 +1207,21 @@ site whose own firewall does that job; the rules are kept, and true
 puts them back. Changed in the cluster's settings, it is in force on
 every node and control plane within seconds.
 
+## GPUNeed
+
+### `min_compute_capability`
+
+`float64`
+
+MinComputeCapability is the oldest architecture that runs it: 7.5 is
+Turing, 8.0 Ampere (bf16, flash-attention 2), 8.9 Ada (fp8), 9.0 Hopper.
+
+### `min_memory_gb`
+
+`int`
+
+MinMemoryGB is the card's own memory it needs.
+
 ## GuardModel
 
 ### `format`
@@ -2316,6 +2336,8 @@ GPU says what card the profile needs, in place of naming its class:
 it stands for every class in the cluster that meets it. A catalog
 entry written once then places sensibly on any site's cards.
 
+Takes a [GPUNeed](#gpuneed) block.
+
 ### `comfyui`
 
 `*ProfileComfyUI`
@@ -2323,6 +2345,22 @@ entry written once then places sensibly on any site's cards.
 ComfyUI is this profile's own workflow, checkpoint and nodes, over the
 model's: an fp8 workflow where the card has fp8, fp16 where it has not.
 
+Takes a [ProfileComfyUI](#profilecomfyui) block.
+
+## ProfileComfyUI
+
+### `workflow`
+
+`string`
+
+### `checkpoint`
+
+`string`
+
+### `nodes`
+
+`[]CustomNode`
+
 ## Router
 
 ### `activation_wait`

internal/docgen/reference_gen.go

@@ -148,6 +148,10 @@ var Reference = []Block{
 	{Package: "config", Name: "FirewallSettings", Title: "FirewallSettings", Doc: "", Fields: []Field{
 		{Key: "enabled", Type: "bool", Doc: "Enabled keeps llmgw's internal ports — engines, node exporter, the\nagents' stream, the mirror, the store — to the cluster's networks on\nevery machine. False removes llmgw's nftables table everywhere, for a\nsite whose own firewall does that job; the rules are kept, and true\nputs them back. Changed in the cluster's settings, it is in force on\nevery node and control plane within seconds.", Nested: ""},
 	}},
+	{Package: "catalog", Name: "GPUNeed", Title: "GPUNeed", Doc: "", Fields: []Field{
+		{Key: "min_compute_capability", Type: "float64", Doc: "MinComputeCapability is the oldest architecture that runs it: 7.5 is\nTuring, 8.0 Ampere (bf16, flash-attention 2), 8.9 Ada (fp8), 9.0 Hopper.", Nested: ""},
+		{Key: "min_memory_gb", Type: "int", Doc: "MinMemoryGB is the card's own memory it needs.", Nested: ""},
+	}},
 	{Package: "catalog", Name: "GuardModel", Title: "GuardModel", Doc: "", Fields: []Field{
 		{Key: "format", Type: "string", Doc: "Format is qwen3guard (Qwen3Guard-Gen: \"Safety: Safe\", \"Unsafe\" or\n\"Controversial\", and the categories), llamaguard3 (Meta's Llama Guard\n3: \"safe\", or \"unsafe\" and the categories), shieldgemma (Google's\nShieldGemma: Yes or No), or json ({\"safe\": false, \"categories\":\n[\"...\"]}).", Nested: ""},
 		{Key: "categories", Type: "[]string", Doc: "Categories the model is asked about, for shieldgemma — each a policy\nsentence — and the names reported for llamaguard3's S1, S2, ….", Nested: ""},
@@ -337,6 +341,11 @@ var Reference = []Block{
 		{Key: "gpu", Type: "*GPUNeed", Doc: "GPU says what card the profile needs, in place of naming its class:\nit stands for every class in the cluster that meets it. A catalog\nentry written once then places sensibly on any site's cards.", Nested: "catalog.GPUNeed"},
 		{Key: "comfyui", Type: "*ProfileComfyUI", Doc: "ComfyUI is this profile's own workflow, checkpoint and nodes, over the\nmodel's: an fp8 workflow where the card has fp8, fp16 where it has not.", Nested: "catalog.ProfileComfyUI"},
 	}},
+	{Package: "catalog", Name: "ProfileComfyUI", Title: "ProfileComfyUI", Doc: "", Fields: []Field{
+		{Key: "workflow", Type: "string", Doc: "", Nested: ""},
+		{Key: "checkpoint", Type: "string", Doc: "", Nested: ""},
+		{Key: "nodes", Type: "[]CustomNode", Doc: "", Nested: ""},
+	}},
 	{Package: "config", Name: "Router", Title: "Router", Doc: "", Fields: []Field{
 		{Key: "activation_wait", Type: "time.Duration", Doc: "ActivationWait is how long a request waits for an on-demand model to\nload before the client is told to come back. Zero takes the default.\n\nThe one real decision in on-demand loading. Refusing outright makes the\nfeature useless, since the first request for every model would fail;\nwaiting without a bound turns a request into a job, and a client that\nbudgeted thirty seconds ends up holding a connection for ten minutes.", Nested: ""},
 		{Key: "scrape_interval", Type: "time.Duration", Doc: "", Nested: ""},

internal/docgen/render.go

@@ -27,6 +27,7 @@ var Sources = []string{
 	"internal/tlsconf/tlsconf.go",
 	"internal/control/catalog/catalog.go",
 	"internal/control/catalog/workflow.go",
+	"internal/control/catalog/hardware.go",
 	"internal/router/admission/controller.go",
 	"internal/accounting/cost.go",
 	"internal/guard/policy.go",