Strata's DeepSeek not offered on cards its engine was not built for, and refused there by the agent

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

BACKLOG.md

@@ -1896,6 +1896,8 @@ served only from a definition written by hand. In order:
 **C. Operating it.**
 - N9. `ctl engine-check strata`: the flags of setup.py and server.py, which drift between versions.
 - N10. `ctl engine-build NODE strata cuda12|cuda13`, as vLLM has.
+- N11a. Strata's per-replica state directories (engine-home/strata/<replica>) are left behind when a replica stops;
+  remove them with it.
 - N11. Disk for the prepared pack and draft layer (and DeepSeek V4.1's 240–280 GB), cleaned with the weights; a
   first start's preparation within the startup timeout.
 - N12. docs/install.md: Strata in the engines table, a section with a profile, its memory and first-run time;

CHANGELOG.md

@@ -40,6 +40,9 @@ APIs change between minors without a deprecation period.
 
 - **A repository that keeps each quantisation in a directory of its own** (ISTA-DASLab's `IQ2_XS/`, `IQ3_S/`) listed
   no weights: its file tree is now read recursively, by the explorer, the plan and `ctl model serve`.
+- **DeepSeek V4.1 offered on a card its engine was not built for.** Strata's DeepSeek engine runs on RTX 30 (compute
+  8.6) and newer; on a Turing card the tab and the plan offered it, and Strata's setup refused it once placed. Now
+  neither offers it there, the tab says why, and the agent refuses such a profile before starting it.
 
 ## v0.16.0 — 2026-10-30
 

internal/agent/engines/strata.go

@@ -9,6 +9,8 @@ import (
 	"regexp"
 	"strconv"
 	"sync/atomic"
+
+	"gitea.mynodes.xyz/ilker/llmgw/internal/strata"
 )
 
 // StrataConfig locates a Strata installation.
@@ -133,6 +135,13 @@ func (*Strata) Validate(p Profile, gpus []GPUInfo) error {
 	if err := requireComputeCapability(p, gpus, 6.0, "strata"); err != nil {
 		return err
 	}
+	// A family whose engine needs more: said now, rather than by Strata's
+	// setup after the replica was placed here.
+	if fam, ok := strata.FamilyNamed(strata.ArgValue(p.Args, "--family")); ok && fam.MinCC > 0 {
+		if err := requireComputeCapability(p, gpus, fam.MinCC, "strata's "+fam.Title+" engine"); err != nil {
+			return err
+		}
+	}
 	return validateCommon(p, gpus)
 }
 

internal/agent/engines/strata_test.go

@@ -98,3 +98,16 @@ func TestAStrataNamedByHandIsReportedWithItsVersion(t *testing.T) {
 		t.Error("reported without its engine")
 	}
 }
+
+func TestStrataRefusesDeepSeekOnACardItsEngineWasNotBuiltFor(t *testing.T) {
+	s := &Strata{}
+	p := Profile{Name: "p", Engine: "strata", ModelPath: "/m", TP: 1, GPUsPerNode: 1, Args: []string{"--family", "deepseek41", "--size", "IST-DAS-1.75bpw"}}
+	gpus := []GPUInfo{{Index: 0, Name: "Quadro RTX 6000", ComputeCapability: "7.5"}}
+	if err := s.Validate(p, gpus); err == nil || !strings.Contains(err.Error(), "8.6") {
+		t.Errorf("DeepSeek on 7.5: %v", err)
+	}
+	p.Args = []string{"--family", "qwen", "--size", "IQ2_XS"}
+	if err := s.Validate(p, gpus); err != nil {
+		t.Errorf("Qwen on 7.5: %v", err)
+	}
+}

internal/control/adminapi/api.go

@@ -1954,6 +1954,11 @@ func PoolNodesOf(nodes []NodeView) []modelplan.PoolNode {
 		if len(n.Fabrics) > 0 {
 			p.Fabric = n.Fabrics[0]
 		}
+		for _, c := range n.ComputeCapabilities {
+			if v, err := strconv.ParseFloat(c, 64); err == nil && v > p.CC {
+				p.CC = v
+			}
+		}
 		if l := n.Load; l != nil && l.MemTotal > 0 {
 			p.HostFreeGB = int((l.MemTotal - l.MemUsed) >> 30)
 		}

internal/modelplan/options.go

@@ -55,6 +55,8 @@ type PoolNode struct {
 	Kinds []PoolKind
 	// Engines are the engines the node has installed.
 	Engines []string
+	// CC is its newest card's compute capability, 0 when not known.
+	CC float64
 }
 
 // PoolKind is one class of a node's devices.

internal/modelplan/strata.go

@@ -24,12 +24,18 @@ func StrataOptions(family string, arts []Artifact, nodes []PoolNode) []Option {
 			continue
 		}
 		need := float64(size.MemoryGB())
+		fam, _ := strata.FamilyNamed(family)
 		byClass := map[string]*Option{}
 		var order []string
 		for _, n := range nodes {
 			if !slices.Contains(n.Engines, "strata") || n.HostMemGB <= 0 {
 				continue
 			}
+			// A family whose engine needs a newer card: refused by Strata on
+			// this one, after the node was chosen.
+			if fam.MinCC > 0 && n.CC > 0 && n.CC < fam.MinCC {
+				continue
+			}
 			have := float64(n.HostMemGB) * hostShare
 			if need > have {
 				continue

internal/modelplan/strata_test.go

@@ -30,3 +30,22 @@ func TestStrataIsOfferedOnANodeWithItTheCardAndTheRAM(t *testing.T) {
 		t.Errorf("%q %q", o.Label(), o.MemoryText())
 	}
 }
+
+// DeepSeek's engine is built for RTX 30 and newer: not offered on a Turing
+// card, which Strata's setup refuses after the replica is placed.
+func TestDeepSeekOnStrataNeedsANewerCard(t *testing.T) {
+	arts := []Artifact{{Name: "IST-DAS-1.75bpw.gguf", Format: "gguf"}}
+	node := func(cc float64) []PoolNode {
+		return []PoolNode{{ID: "n", Class: "6000-24g", GPUMemGB: 24, GPUs: 1, FreeGPUs: 1, HostMemGB: 251,
+			Engines: []string{"strata"}, CC: cc}}
+	}
+	if got := StrataOptions("deepseek41", arts, node(7.5)); len(got) != 0 {
+		t.Errorf("offered on 7.5: %+v", got)
+	}
+	if got := StrataOptions("deepseek41", arts, node(8.9)); len(got) != 1 {
+		t.Errorf("not offered on 8.9: %+v", got)
+	}
+	if got := StrataOptions("qwen", []Artifact{{Name: "IQ2_XS.gguf"}}, node(7.5)); len(got) != 1 {
+		t.Errorf("Qwen not offered on 7.5: %+v", got)
+	}
+}

internal/strata/models.go

@@ -26,6 +26,10 @@ type Family struct {
 	// Engine is a family that runs on an engine path of its own, with a
 	// download of its own (DeepSeek V4.1).
 	Engine bool
+	// MinCC is the compute capability its engine needs of an NVIDIA card,
+	// above Strata's own 6.0; 0 for none. DeepSeek's engine is built for
+	// RTX 30 (8.6) and newer only.
+	MinCC float64
 }
 
 // Size is one of a family's sizes: setup's --model, which llmgw's profile
@@ -56,7 +60,7 @@ var Families = []Family{
 	{Name: "gyro", Model: "qwen3.8-flash-next-gyro", Title: "Qwen3.8-Flash-Next (Gyro)", Repo: "agentionai/Qwen3.8-Flash-Next-Gyro-GGUF"},
 	{Name: "nvfp4", Model: "qwen3.8-flash-next-nvfp4", Title: "Qwen3.8-Flash-Next (NVFP4)"},
 	{Name: "qwen36", Model: "qwen3.6-35b-a3b", Title: "Qwen3.6-35B-A3B", Repo: "unsloth/Qwen3.6-35B-A3B-MTP-GGUF"},
-	{Name: "deepseek41", Model: "deepseek-v4.1-flash", Title: "DeepSeek V4.1-Flash", Repo: "ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF", Engine: true},
+	{Name: "deepseek41", Model: "deepseek-v4.1-flash", Title: "DeepSeek V4.1-Flash", Repo: "ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF", Engine: true, MinCC: 8.6},
 }
 
 // Sizes are the sizes Strata 0.2.7 runs, and which families have each.

internal/web/admin_strata.go

@@ -65,6 +65,8 @@ func (p *AccountPages) strataView(l *Lang) *strataView {
 				sr.Fits, sr.Runs = true, l.T("explore.strata", opts[0].Class, l.Num(opts[0].NeedGB, 0))
 			case len(v.Nodes) == 0:
 				sr.Runs = l.T("strata.no_node")
+			case f.MinCC > 0 && cardsOlderThan(pool, f.MinCC):
+				sr.Runs = l.T("strata.old_card", l.Num(f.MinCC, 1))
 			default:
 				sr.Runs = l.T("strata.no_room", s.MemoryGB())
 			}
@@ -75,6 +77,22 @@ func (p *AccountPages) strataView(l *Lang) *strataView {
 	return v
 }
 
+// cardsOlderThan says whether every node with Strata has a card of a
+// compute capability below cc, as far as they say.
+func cardsOlderThan(pool []modelplan.PoolNode, cc float64) bool {
+	older := false
+	for _, n := range pool {
+		if !slices.Contains(n.Engines, "strata") {
+			continue
+		}
+		if n.CC == 0 || n.CC >= cc {
+			return false
+		}
+		older = true
+	}
+	return older
+}
+
 // serveStrata adds a model of a family Strata fetches itself: its source
 // the repository, its replica on a card of the class the plan found.
 func (p *AccountPages) serveStrata(ctx context.Context, l *Lang, by, family, size string) (string, error) {

internal/web/admin_strata_test.go

@@ -15,7 +15,7 @@ type strataFleet struct{ fakeFleet }
 
 func (strataFleet) Nodes() []adminapi.NodeView {
 	return []adminapi.NodeView{{ID: "cuda01", State: "ready", GPUTotal: 1, GPUFree: 1, MemoryGB: 251,
-		Classes: []string{"6000-24g"}, Engines: []string{"llamacpp", "strata"}}}
+		Classes: []string{"6000-24g"}, Engines: []string{"llamacpp", "strata"}, ComputeCapabilities: []string{"7.5"}}}
 }
 
 func TestTheStrataTabListsWhatRunsHereAndFetchesASize(t *testing.T) {
@@ -31,13 +31,14 @@ func TestTheStrataTabListsWhatRunsHereAndFetchesASize(t *testing.T) {
 
 	body := mirrorGet(t, mux, "/admin/mirror?tab=strata").Body.String()
 	for _, want := range []string{"Strata is installed on: cuda01", "Qwen3.8-Flash-Next", "IQ2_XS",
-		"1× 6000-24g with Strata, 52 GB of RAM", `name="size" value="IQ2_XS"`, "Strata fetches these onto the node itself"} {
+		"1× 6000-24g with Strata, 52 GB of RAM", `name="size" value="IQ2_XS"`, "Strata fetches these onto the node itself",
+		"compute capability 8.6 or newer"} {
 		if !strings.Contains(body, want) {
 			t.Errorf("the tab lacks %q", want)
 		}
 	}
 	// Unsloth's Q8_0 keeps 140 GB: it runs here; nothing past the node's RAM does.
-	if strings.Contains(body, `value="UD-Q8_K_XL"`) {
+	if strings.Contains(body, `value="UD-Q8_K_XL"`) || strings.Contains(body, `value="IST-DAS-1.75bpw"`) {
 		t.Error("offered DeepSeek's 306 GB size, which no node holds, and which Strata fetches itself")
 	}
 

internal/web/locales/en/mirror.json

@@ -278,5 +278,6 @@
   "strata.err.not_servable": "%s is fetched into the mirror first, then served from its version",
   "strata.msg.served": "%s added: its first start fetches about %s GB onto the node and prepares it, which can take hours on a slow link; Replicas shows how far it is.",
   "strata.pack_files": "part of Strata's ready-made %s %s pack: served whole from the mirror's Strata tab, Strata fetching it onto the node",
-  "strata.unknown_pack": "a pack made for Strata that Strata 0.2.7 does not know: its setup refuses it, and llama.cpp cannot read it"
+  "strata.unknown_pack": "a pack made for Strata that Strata 0.2.7 does not know: its setup refuses it, and llama.cpp cannot read it",
+  "strata.old_card": "its engine needs an NVIDIA card of compute capability %s or newer (RTX 30 on); the nodes with Strata have older ones"
 }

internal/web/locales/tr/mirror.json

@@ -271,5 +271,6 @@
   "strata.err.not_servable": "%s önce aynaya indirilir, sonra sürümünden sunulur",
   "strata.msg.served": "%s eklendi: ilk açılışında node'a yaklaşık %s GB indirip hazırlar; yavaş bağlantıda saatler sürebilir. İlerleyişi Replikalar gösterir.",
   "strata.pack_files": "Strata'nın hazır %s %s paketinin parçası: aynanın Strata sekmesinden bütün olarak sunulur, Strata onu node'a kendisi indirir",
-  "strata.unknown_pack": "Strata için hazırlanmış ama Strata 0.2.7'nin tanımadığı bir paket: kurulumu onu reddeder, llama.cpp de okuyamaz"
+  "strata.unknown_pack": "Strata için hazırlanmış ama Strata 0.2.7'nin tanımadığı bir paket: kurulumu onu reddeder, llama.cpp de okuyamaz",
+  "strata.old_card": "motoru compute capability %s ya da daha yeni bir NVIDIA kartı ister (RTX 30 ve sonrası); Strata kurulu node'ların kartları daha eski"
 }