Ilker ManapandClaude Opus 5.5
f41c96d30f
CI / test (push) Successful in 9m42s
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
52 lines
2.2 KiB
Go
52 lines
2.2 KiB
Go
package modelplan
|
||
|
||
import "testing"
|
||
|
||
func TestStrataIsOfferedOnANodeWithItTheCardAndTheRAM(t *testing.T) {
|
||
arts := []Artifact{{Name: "Qwen3.8-Flash-Next-GSQ-RCO-IQ2_XS-00001-of-00002.gguf", Format: "gguf", Bytes: 68e9},
|
||
{Name: "something-else-Q4_K_M.gguf", Format: "gguf", Bytes: 5e9}}
|
||
nodes := []PoolNode{
|
||
{ID: "cuda01", Class: "6000-24g", GPUMemGB: 24, GPUs: 1, FreeGPUs: 1, HostMemGB: 251, HostFreeGB: 200,
|
||
Engines: []string{"llamacpp", "strata"}},
|
||
{ID: "no-strata", Class: "6000-24g", GPUMemGB: 24, GPUs: 1, FreeGPUs: 1, HostMemGB: 251, Engines: []string{"llamacpp"}},
|
||
{ID: "small-ram", Class: "6000-24g", GPUMemGB: 24, GPUs: 1, FreeGPUs: 1, HostMemGB: 32, Engines: []string{"strata"}},
|
||
{ID: "small-card", Class: "t4-8g", GPUMemGB: 8, GPUs: 1, FreeGPUs: 1, HostMemGB: 251, Engines: []string{"strata"}},
|
||
}
|
||
opts := StrataOptions("qwen", arts, nodes)
|
||
if len(opts) != 1 {
|
||
t.Fatalf("%+v", opts)
|
||
}
|
||
o := opts[0]
|
||
if o.Engine != "strata" || o.StrataSize != "IQ2_XS" || o.Hosts != 1 || !o.FreeNow || o.NeedGB != 52 || o.GPUs() != 1 {
|
||
t.Errorf("%+v", o)
|
||
}
|
||
// It ranks before llama.cpp on the CPU, and says what it needs.
|
||
all := append(Options(arts[:1], Shape{}, nodes, 16384), opts...)
|
||
Rank(all)
|
||
if all[0].Engine != "strata" {
|
||
t.Errorf("first is %+v", all[0])
|
||
}
|
||
if o.Label() != "1 × 6000-24g with Strata, experts in RAM" || o.MemoryText() == "" {
|
||
t.Errorf("%q %q", o.Label(), o.MemoryText())
|
||
}
|
||
}
|
||
|
||
// DeepSeek's engine is built for RTX 30 and newer: not offered on a Turing
|
||
// card, which Strata's setup refuses after the replica is placed.
|
||
func TestDeepSeekOnStrataNeedsANewerCard(t *testing.T) {
|
||
arts := []Artifact{{Name: "IST-DAS-1.75bpw.gguf", Format: "gguf"}}
|
||
node := func(cc float64) []PoolNode {
|
||
return []PoolNode{{ID: "n", Class: "6000-24g", GPUMemGB: 24, GPUs: 1, FreeGPUs: 1, HostMemGB: 251,
|
||
Engines: []string{"strata"}, CC: cc}}
|
||
}
|
||
if got := StrataOptions("deepseek41", arts, node(7.5)); len(got) != 0 {
|
||
t.Errorf("offered on 7.5: %+v", got)
|
||
}
|
||
if got := StrataOptions("deepseek41", arts, node(8.9)); len(got) != 1 {
|
||
t.Errorf("not offered on 8.9: %+v", got)
|
||
}
|
||
if got := StrataOptions("qwen", []Artifact{{Name: "IQ2_XS.gguf"}}, node(7.5)); len(got) != 1 {
|
||
t.Errorf("Qwen not offered on 7.5: %+v", got)
|
||
}
|
||
}
|