test(config): injectable local-GPU seam + single-instance coverage

Make local GPU detection an injectable package var (localGPU) so the
single-instance path (SetDefaults -> ApplyHardwareDefaults) is deterministically
testable without a real GPU, mirroring the distributed override's coverage.
Adds specs asserting SetDefaults sets the Blackwell physical batch, leaves it
unset on non-Blackwell, and never overrides an explicit batch.

Assisted-by: Claude:opus-4.8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

core/config/hardware_defaults.go

@@ -70,10 +70,11 @@ func IsManagedPhysicalBatch(n int) bool {
 	return n == DefaultPhysicalBatch || n == BlackwellPhysicalBatch
 }
 
-// LocalGPU builds a GPU descriptor from local detection. Used by SetDefaults on
-// a single host; the distributed router builds the descriptor from the selected
-// node's reported info instead.
-func LocalGPU() GPU {
+// localGPU builds a GPU descriptor from local detection, used by SetDefaults on
+// a single host (the distributed router builds it from the selected node's
+// reported info instead). It is a package var so tests can inject a
+// deterministic device — detection does a live nvidia-smi call.
+var localGPU = func() GPU {
 	vendor, _ := xsysinfo.DetectGPUVendor()
 	return GPU{
 		Vendor:            vendor,

core/config/hardware_defaults_internal_test.go

@@ -0,0 +1,37 @@
+package config
+
+import (
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+// Single-instance path: SetDefaults applies hardware defaults from the local
+// GPU. The detection seam (localGPU) is injected so the path is deterministic
+// without a real GPU.
+var _ = Describe("SetDefaults hardware defaults (single-instance)", func() {
+	var orig func() GPU
+	BeforeEach(func() { orig = localGPU })
+	AfterEach(func() { localGPU = orig })
+
+	It("sets the physical batch on a local Blackwell GPU", func() {
+		localGPU = func() GPU { return GPU{ComputeCapability: "12.1"} }
+		cfg := &ModelConfig{}
+		cfg.SetDefaults()
+		Expect(cfg.Batch).To(Equal(BlackwellPhysicalBatch))
+	})
+
+	It("leaves batch unset on a non-Blackwell local GPU", func() {
+		localGPU = func() GPU { return GPU{ComputeCapability: "8.9"} }
+		cfg := &ModelConfig{}
+		cfg.SetDefaults()
+		Expect(cfg.Batch).To(Equal(0))
+	})
+
+	It("never overrides an explicit batch", func() {
+		localGPU = func() GPU { return GPU{ComputeCapability: "12.1"} }
+		cfg := &ModelConfig{}
+		cfg.Batch = 1024
+		cfg.SetDefaults()
+		Expect(cfg.Batch).To(Equal(1024))
+	})
+})

core/config/model_config.go

@@ -1114,7 +1114,7 @@ func (cfg *ModelConfig) SetDefaults(opts ...ConfigLoaderOption) {
 	// Apply hardware-driven defaults (e.g. a larger physical batch on Blackwell).
 	// Uses the local GPU here; in distributed mode the router re-applies the same
 	// heuristics for the selected node's GPU before loading. Explicit config wins.
-	ApplyHardwareDefaults(cfg, LocalGPU())
+	ApplyHardwareDefaults(cfg, localGPU())
 
 	// https://github.com/ggerganov/llama.cpp/blob/75cd4c77292034ecec587ecb401366f57338f7c0/common/sampling.h#L22
 	defaultTopP := 0.95