Ilker ManapandClaude Opus 5.5
845de8eef4
CI / test (push) Successful in 10m35s
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
53 lines
2.3 KiB
Go
53 lines
2.3 KiB
Go
package modelserve
|
|
|
|
import (
|
|
"slices"
|
|
"strings"
|
|
"testing"
|
|
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/hf"
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/modelplan"
|
|
)
|
|
|
|
func TestAStrataWayIsChosenAndMadeAProfile(t *testing.T) {
|
|
set := hf.FileSet{Name: "Qwen3.8-Flash-Next-GSQ-RCO-IQ2_XS-00001-of-00002.gguf"}
|
|
strataWay := modelplan.Option{Artifact: set.Name, Format: "gguf", Engine: "strata", Class: "6000-24g",
|
|
GPUsPerNode: 1, Nodes: 1, NeedGB: 52, HaveGB: 213, Hosts: 1, StrataFamily: "qwen", StrataSize: "IQ2_XS"}
|
|
cpuWay := modelplan.Option{Artifact: set.Name, Format: "gguf", Engine: "llamacpp", CPU: true, NeedGB: 75, HaveGB: 213, Hosts: 1}
|
|
plan := Plan{Repo: "ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF", Options: []modelplan.Option{strataWay, cpuWay}}
|
|
|
|
got, err := chooseLayout(Request{Format: "gguf", Fallbacks: true}, plan, true, set)
|
|
if err != nil || len(got) != 1 || got[0].Engine != "strata" {
|
|
t.Fatalf("the plan's best, without llama.cpp fallbacks: %+v %v", got, err)
|
|
}
|
|
if got, _ := chooseLayout(Request{Format: "gguf", Engine: "llamacpp"}, plan, true, set); len(got) != 1 || !got[0].CPU {
|
|
t.Errorf("kept off Strata: %+v", got)
|
|
}
|
|
if _, err := chooseLayout(Request{Format: "gguf", Engine: "strata", GPUClass: "h100-80g"}, plan, true, set); err == nil {
|
|
t.Error("Strata on a class it was not planned for")
|
|
}
|
|
|
|
ps := profilesFor(got, Request{ContextLength: 32768}, 0, 0)
|
|
p := ps[0]
|
|
if p.Engine != "strata" || p.GPUClass != "6000-24g" || p.GPUsPerNode != 1 || p.MinMemoryGB != 52 ||
|
|
!slices.Equal(p.Args, []string{"--family", "qwen", "--size", "IQ2_XS", "--context", "32768", "--vision", "no"}) ||
|
|
!strings.HasPrefix(p.Name, "strata-") {
|
|
t.Errorf("%+v", p)
|
|
}
|
|
}
|
|
|
|
func TestAReadyMadePackIsPlannedOnStrataOnly(t *testing.T) {
|
|
s := New(Deps{Pool: func() []modelplan.PoolNode {
|
|
return []modelplan.PoolNode{{ID: "cuda01", Class: "6000-24g", GPUMemGB: 24, GPUs: 1, FreeGPUs: 1,
|
|
HostMemGB: 251, HostFreeGB: 200, Engines: []string{"strata"}}}
|
|
}})
|
|
p, err := s.plan(t.Context(), hf.Repo{ID: "Maximilian228/Qwen3.8-Flash-Next-NVIDIA-NVFP4-Strata", Revision: "abc",
|
|
Architecture: "strata-ple"}, PlanRequest{})
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if !p.Servable || len(p.Options) != 1 || p.Options[0].StrataFamily != "nvfp4" || p.Options[0].StrataSize != "NVFP4-NVIDIA" {
|
|
t.Errorf("%+v", p)
|
|
}
|
|
}
|