Scale and place by what a replica was measured to serve
Stored ctl bench results reach the reconciler: requests per replica past the measured SLO concurrency scale a model up, a replica is taken back only if the rest stay under 70% of theirs, and among profiles of equal priority the most measured tokens per GPU or core is tried first. ctl model target sizes a model for a throughput against the room there is. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
9dc1b62fdc
commit
78e41460f9
16 files changed
+503
-15
No files matched your search
@@ -0,0 +1,30 @@
|
||||
package adminapi
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"gitea.mynodes.xyz/ilker/llmgw/internal/control/reconciler"
|
||||
)
|
||||
|
||||
func TestATargetIsSizedFromTheMeasurementAndTheRoom(t *testing.T) {
|
||||
// Three 8-GPU nodes; one tp8 replica was measured at 500 tokens/s.
|
||||
a, ctl := setup(t, testModels(), gpuNode("1", 8), gpuNode("2", 8), gpuNode("3", 8))
|
||||
if _, err := a.Target("llama", 1000); err == nil || !strings.Contains(err.Error(), "ctl bench llama --save") {
|
||||
t.Errorf("an unmeasured model should say how to measure it: %v", err)
|
||||
}
|
||||
ctl.Reconciler().SetMeasurements(func() map[string]reconciler.Measured {
|
||||
return map[string]reconciler.Measured{"llama/tp8": {MaxConcurrency: 16, TokPerSec: 500}}
|
||||
})
|
||||
v, err := a.Target("llama", 1200)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if v.Needed != 3 || v.PerReplica != 500 || v.Profile != "tp8" || v.More != 3 || !v.Fits {
|
||||
t.Errorf("1200 tok/s at 500 each is 3 replicas on 3 empty nodes: %+v", v)
|
||||
}
|
||||
v, _ = a.Target("llama", 2000)
|
||||
if v.Needed != 4 || v.Fits || v.Room != 3 || len(v.Blocked) == 0 {
|
||||
t.Errorf("a fourth does not fit on three nodes, and should say why: %+v", v)
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user