Ilker ManapandClaude Opus 5.5
4f280a3546
A node that cannot run the CUDA 13 build installs the same version's CUDA 12.9 build from vLLM's GitHub release, with PyTorch's cu129 torch; the install computes on the GPU before it counts. The build can be chosen per node — auto, cu13, cu129, none — on the cluster page, with ctl engine-build, or over the admin API; the control plane keeps the choice and tells the node at once. Refs #2. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
64 lines
2.1 KiB
Go
64 lines
2.1 KiB
Go
package adminapi
|
|
|
|
import (
|
|
"context"
|
|
"log/slog"
|
|
"net/http"
|
|
"testing"
|
|
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/control"
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/control/inventory"
|
|
)
|
|
|
|
// choiceStore keeps engine choices in memory.
|
|
type choiceStore struct{ m map[string]map[string]string }
|
|
|
|
func (c *choiceStore) NodeEngines(context.Context) (map[string]map[string]string, error) {
|
|
return c.m, nil
|
|
}
|
|
func (c *choiceStore) SetNodeEngine(_ context.Context, node, engine, variant, _ string) error {
|
|
if c.m[node] == nil {
|
|
c.m[node] = map[string]string{}
|
|
}
|
|
c.m[node][engine] = variant
|
|
return nil
|
|
}
|
|
|
|
func TestAnEngineBuildIsChosenForANodeAndTheNodeIsTold(t *testing.T) {
|
|
a, ctl := setup(t, testModels(), gpuNode("gpu07", 8), inventory.Node{ID: "cpu01", State: inventory.Ready})
|
|
ch := control.NewEngineChoices(t.Context(), &choiceStore{m: map[string]map[string]string{}}, slog.New(slog.DiscardHandler))
|
|
var told []string
|
|
ch.OnChange(func(node string) error { told = append(told, node); return nil })
|
|
ctl.SetEngineChoices(ch)
|
|
|
|
if code := call(t, a, http.MethodPost, "/api/v1/nodes/gpu07/engines", `{"engine":"vllm","build":"cu129"}`, nil); code != http.StatusOK {
|
|
t.Fatalf("status %d", code)
|
|
}
|
|
if len(told) != 1 || told[0] != "gpu07" {
|
|
t.Errorf("the node was not told: %v", told)
|
|
}
|
|
var nodes []NodeView
|
|
call(t, a, http.MethodGet, "/api/v1/nodes", "", &nodes)
|
|
for _, n := range nodes {
|
|
switch n.ID {
|
|
case "gpu07":
|
|
if n.EngineBuilds["vllm"] != "cu129" {
|
|
t.Errorf("gpu07 shows %v", n.EngineBuilds)
|
|
}
|
|
case "cpu01":
|
|
if n.EngineBuilds != nil {
|
|
t.Errorf("a node with no GPU has no build to choose: %v", n.EngineBuilds)
|
|
}
|
|
}
|
|
}
|
|
for _, bad := range []string{`{"engine":"vllm","build":"cu200"}`, `{"engine":"llamacpp","build":"cu129"}`} {
|
|
if code := call(t, a, http.MethodPost, "/api/v1/nodes/gpu07/engines", bad, nil); code != http.StatusBadRequest {
|
|
t.Errorf("%s: status %d", bad, code)
|
|
}
|
|
}
|
|
if code := call(t, a, http.MethodPost, "/api/v1/nodes/gpu07/engines", `{"engine":"vllm","build":"auto"}`, nil); code != http.StatusOK ||
|
|
ch.For("gpu07")["vllm"] != "" {
|
|
t.Errorf("auto should leave it to the node again: %d %v", code, ch.For("gpu07"))
|
|
}
|
|
}
|