A replica says what its engine computes on, and llama.cpp's word on the CPU refuses a GPU placement

llama.cpp's start-up output is read as a shard becomes ready: the devices it
used, its backend, and the layers it offloaded. That goes up with READY in a
new ShardStatus.compute, is kept on the shard, and is shown by the admin
API, ctl replicas (ON) and the console (COMPUTE). A shard given GPUs whose
engine says it found no usable GPU or offloaded no layer is stopped and
failed, even where nvidia-smi cannot be asked.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-10-07 13:02:17 +02:00
1 parent f285aa0548
commit 0bd0d881c5
15 files changed
+517 -126

No files matched your search

+6 -2
View File
@@ -1230,13 +1230,17 @@ func (m consoleModel) panel() (title, body, keys string) {
for _, s := range r.Shards {
nodes = append(nodes, fmt.Sprintf("%s%v", s.Node, discovery.DeviceLabels(s.GPUs)))
}
rows = append(rows, []string{r.ID, r.Model, r.State, r.Pool, strings.Join(nodes, " "),
compute := "-"
if len(r.Shards) > 0 {
compute = r.Shards[0].Compute.Short()
}
rows = append(rows, []string{r.ID, r.Model, r.State, r.Pool, compute, strings.Join(nodes, " "),
(time.Duration(r.AgeSec) * time.Second).Round(time.Second).String()})
}
if m.inPanel {
keys = rowKeys
}
return "Replicas", "\n" + table([]string{"REPLICA", "MODEL", "STATE", "POOL", "ON", "AGE"}, rows, m.row, pw, m.inPanel), keys
return "Replicas", "\n" + table([]string{"REPLICA", "MODEL", "STATE", "POOL", "COMPUTE", "ON", "AGE"}, rows, m.row, pw, m.inPanel), keys
case cUsage:
head := "\n Last 24 hours, by " + lipgloss.NewStyle().Bold(true).Render(usageGroupings[m.usageBy]) +
sDim.Render(" (→ to group by "+usageGroupings[(m.usageBy+1)%len(usageGroupings)]+")") + "\n\n"