Ilker ManapandClaude Opus 5.5
2a1e0e6c4c
A vLLM model can carry PEFT adapters, registered at start, or with max_loaded_adapters held at most N per replica: the router loads an adapter through vLLM's runtime LoRA API when a request first wants it, sends the adapter's requests to a replica that holds it while that one is not saturated, loads each cold adapter once, and unloads the least recently used idle one to make room. llama.cpp keeps loading every adapter at start. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
66 lines
2.1 KiB
Go
66 lines
2.1 KiB
Go
package catalog
|
|
|
|
import (
|
|
"slices"
|
|
"strings"
|
|
"testing"
|
|
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/agent/engines"
|
|
)
|
|
|
|
func loraModel(engine string, limit int) Model {
|
|
m := model("coder", Profile{Name: "p", Engine: engine, GPUClass: "h100-80g", TP: 1})
|
|
m.Adapters = []Adapter{{Name: "coder-sql", Source: "http://mirror/coder-sql/v1/"}}
|
|
m.MaxLoadedAdapters = limit
|
|
return m
|
|
}
|
|
|
|
func TestAdaptersLoadOnDemandOnVLLMOnly(t *testing.T) {
|
|
if _, err := New([]Model{loraModel("vllm", 4)}); err != nil {
|
|
t.Errorf("vLLM with a cap: %v", err)
|
|
}
|
|
if _, err := New([]Model{loraModel("vllm", 0)}); err != nil {
|
|
t.Errorf("vLLM loading every adapter at start: %v", err)
|
|
}
|
|
_, err := New([]Model{loraModel("llamacpp", 4)})
|
|
if err == nil || !strings.Contains(err.Error(), "max_loaded_adapters needs vllm") {
|
|
t.Errorf("llama.cpp with a cap: %v", err)
|
|
}
|
|
if _, err := New([]Model{loraModel("vllm", -1)}); err == nil {
|
|
t.Error("a negative cap was accepted")
|
|
}
|
|
}
|
|
|
|
func TestRuntimeLoadingCannotBeTurnedOnByHand(t *testing.T) {
|
|
m := loraModel("vllm", 0)
|
|
m.Profiles[0].Env = map[string]string{engines.RuntimeLoRAEnv: "True"}
|
|
if _, err := New([]Model{m}); err == nil || !strings.Contains(err.Error(), "max_loaded_adapters") {
|
|
t.Errorf("want a pointer to max_loaded_adapters, got %v", err)
|
|
}
|
|
}
|
|
|
|
func TestAnAdapterThatLoadsOnDemandIsNamedLikeAFile(t *testing.T) {
|
|
m := loraModel("vllm", 2)
|
|
m.Adapters[0].Name = "team/sql"
|
|
if _, err := New([]Model{m}); err == nil {
|
|
t.Error("an adapter with a slash in its name was accepted")
|
|
}
|
|
m.MaxLoadedAdapters = 0
|
|
if _, err := New([]Model{m}); err != nil {
|
|
t.Errorf("loaded at start, the name names no file: %v", err)
|
|
}
|
|
}
|
|
|
|
func TestTheEngineProfileOfAModelWithACapStartsVLLMReadyToLoad(t *testing.T) {
|
|
p, ok := loraModel("vllm", 3).EngineProfile("p")
|
|
if !ok {
|
|
t.Fatal("no profile")
|
|
}
|
|
if !p.RuntimeLoRA() || !slices.Equal(p.Args, []string{"--max-loras", "3"}) {
|
|
t.Errorf("env %v args %v", p.Env, p.Args)
|
|
}
|
|
if p, _ := loraModel("vllm", 0).EngineProfile("p"); p.RuntimeLoRA() || len(p.Args) != 0 {
|
|
t.Errorf("without a cap: env %v args %v", p.Env, p.Args)
|
|
}
|
|
}
|