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>
83 lines
2.9 KiB
Go
83 lines
2.9 KiB
Go
package agentsvc
|
|
|
|
import (
|
|
"slices"
|
|
"testing"
|
|
|
|
llmgwv1 "gitea.mynodes.xyz/ilker/llmgw/api/gen/llmgw/v1"
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/agent/provision"
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/control/inventory"
|
|
)
|
|
|
|
func TestANodeIsAskedOnlyForEnginesItCanInstall(t *testing.T) {
|
|
// An agent older than the list says nothing, and could install llama.cpp
|
|
// alone. Asked for vLLM, it showed as failing until it was upgraded.
|
|
if got := installable(&llmgwv1.Register{}); !slices.Equal(got, []string{"llamacpp"}) {
|
|
t.Errorf("an agent that said nothing: %v", got)
|
|
}
|
|
// This agent says what it can, and that is vLLM and SGLang besides.
|
|
now := &llmgwv1.Register{InstallableEngines: provision.Installable()}
|
|
for _, e := range []string{"llamacpp", "vllm", "sglang"} {
|
|
if !slices.Contains(installable(now), e) {
|
|
t.Errorf("this agent does not offer %s: %v", e, installable(now))
|
|
}
|
|
}
|
|
if slices.Contains(installable(now), "uv") {
|
|
t.Error("uv, a tool for the others, is offered as an engine")
|
|
}
|
|
}
|
|
|
|
func TestEachNodeIsToldTheEnginesDecidedForIt(t *testing.T) {
|
|
s := &Service{}
|
|
s.SetEnginesFor(func(n inventory.Node) map[string]string {
|
|
if n.ID == "volta" {
|
|
return map[string]string{"llamacpp": "b1", "vllm": "0.25.1"}
|
|
}
|
|
return map[string]string{"llamacpp": "b1", "vllm": "0.30.0"}
|
|
})
|
|
reg := &llmgwv1.Register{InstallableEngines: []string{"llamacpp", "vllm"}}
|
|
want := func(p *llmgwv1.Provision) map[string]string {
|
|
out := map[string]string{}
|
|
for _, e := range p.GetEngines() {
|
|
out[e.GetEngine()] = e.GetVersion()
|
|
}
|
|
return out
|
|
}
|
|
if got := want(s.provisionFor(inventory.Node{ID: "volta"}, installable(reg))); got["vllm"] != "0.25.1" {
|
|
t.Errorf("the Volta node: %v", got)
|
|
}
|
|
if got := want(s.provisionFor(inventory.Node{ID: "hopper"}, installable(reg))); got["vllm"] != "0.30.0" {
|
|
t.Errorf("the Hopper node: %v", got)
|
|
}
|
|
// A node that disabled vLLM does not offer it, and is not asked for it.
|
|
if got := want(s.provisionFor(inventory.Node{ID: "hopper"}, []string{"llamacpp"})); got["vllm"] != "" {
|
|
t.Errorf("asked a node for an engine it does not install: %v", got)
|
|
}
|
|
}
|
|
|
|
func TestABuildChosenForANodeIsWhatItIsTold(t *testing.T) {
|
|
s := &Service{}
|
|
s.SetEngines(map[string]string{"llamacpp": "b1", "vllm": "0.30.0"})
|
|
s.SetEngineChoices(func(node string) map[string]string {
|
|
return map[string]map[string]string{"gpu07": {"vllm": "cu129"}, "gpu08": {"vllm": "none"}}[node]
|
|
})
|
|
can := []string{"llamacpp", "vllm"}
|
|
variant := func(node string) (string, bool) {
|
|
for _, e := range s.provisionFor(inventory.Node{ID: node}, can).GetEngines() {
|
|
if e.GetEngine() == "vllm" {
|
|
return e.GetVariant(), true
|
|
}
|
|
}
|
|
return "", false
|
|
}
|
|
if v, ok := variant("gpu07"); !ok || v != "cu129" {
|
|
t.Errorf("gpu07: %q, %v", v, ok)
|
|
}
|
|
if _, ok := variant("gpu08"); ok {
|
|
t.Error("gpu08 was asked for a vLLM it was chosen to run none of")
|
|
}
|
|
if v, ok := variant("gpu09"); !ok || v != "" {
|
|
t.Errorf("gpu09, left to its hardware: %q, %v", v, ok)
|
|
}
|
|
}
|