Every setting of a served model from the mirror page, and its replicas per profile
CI / test (push) Successful in 10m51s
CI / test (push) Successful in 10m51s
The row of a served model leads to its card, which now changes its context and longest answer, its cards, its replicas on each profile with a profile on CPUs to add and its speed beside, stops, starts and restarts it, and removes it with its files or without. Stopped on the row stops the model rather than setting its scaling to nothing. The console gains Replicas per profile, and ctl models shows the counts. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
e23732fbbb
commit
1a3f385be4
15 files changed
+721
-20
No files matched your search
@@ -108,6 +108,23 @@ type modelUse struct {
|
||||
// Declared models are read from server.yaml on every start, so a mode
|
||||
// changed here would revert; the page says where to change it instead.
|
||||
Declared bool
|
||||
// What its card changes beside: the context and longest answer, whether
|
||||
// it is stopped, its profile on cards and the cards a replica takes.
|
||||
ContextLength, MaxOutput int
|
||||
Stopped bool
|
||||
GPUProfile string
|
||||
GPUs int
|
||||
// Profiles are where its replicas run and, Split, how many on each.
|
||||
Profiles []profileUse
|
||||
Split bool
|
||||
// CanCPU says a profile on CPUs can be added — a llama.cpp model with
|
||||
// none — reserving CPUMemoryGB and NewCPUCores, answering about
|
||||
// CPUSpeed tokens a second on CPUSpeedNode.
|
||||
CanCPU bool
|
||||
CPUMemoryGB int
|
||||
NewCPUCores int
|
||||
CPUSpeed float64
|
||||
CPUSpeedNode string
|
||||
}
|
||||
|
||||
// mirrorRow is one model version as the page shows it.
|
||||
@@ -324,6 +341,18 @@ func (p *AccountPages) RegisterAdminMirror(mux *http.ServeMux, d MirrorDeps) {
|
||||
if name == "" || (mode != modeAlways && mode != modeOnDemand && mode != modeStopped) {
|
||||
return "", errors.New(l.T("mirror.err.choose_mode"))
|
||||
}
|
||||
// Stopped is the model kept as it was, and started again so:
|
||||
// not its scaling set to nothing, which forgot what it was —
|
||||
// and its replicas per profile with it.
|
||||
if mode == modeStopped {
|
||||
if _, err := d.Catalog.Stop(ctx, name, admin.Email); err != nil {
|
||||
return "", err
|
||||
}
|
||||
return l.T("mirror.msg.stopped", name), nil
|
||||
}
|
||||
if _, err := d.Catalog.Start(ctx, name, admin.Email); err == nil && mode == modeAlways {
|
||||
return l.T("mirror.msg.model_started", name), nil
|
||||
}
|
||||
replicas, _ := strconv.Atoi(r.FormValue("replicas"))
|
||||
sc := scalingFor(mode, replicas, 0)
|
||||
if _, err := d.Catalog.Scale(ctx, name, sc, admin.Email); err != nil {
|
||||
@@ -339,6 +368,7 @@ func (p *AccountPages) RegisterAdminMirror(mux *http.ServeMux, d MirrorDeps) {
|
||||
}))
|
||||
|
||||
mux.HandleFunc("POST /admin/mirror/replicas", p.mirrorAction(m, p.setModel))
|
||||
p.registerModelSettings(mux, m)
|
||||
mux.HandleFunc("POST /admin/mirror/adapters", p.mirrorAction(m, p.setAdapters))
|
||||
|
||||
mux.HandleFunc("POST /admin/mirror/serve", p.mirrorAction(m,
|
||||
@@ -565,6 +595,7 @@ func (p *AccountPages) renderMirror(w http.ResponseWriter, r *http.Request,
|
||||
if len(m.Profiles) > 0 {
|
||||
u.MemoryGB, u.CPUCores = m.Profiles[0].MinMemoryGB, m.Profiles[0].CPUCores
|
||||
}
|
||||
p.describeProfiles(&u, m, d.Rows[i].Status)
|
||||
if v, ok := views[m.Name]; ok {
|
||||
u.Fleet, u.Ready, u.Wanted = true, v.Ready, v.Desired
|
||||
u.Parked, u.Unplaceable = v.Parked, v.Unplaceable
|
||||
|
||||
Reference in new issue
Block a user