Found on a fresh three-machine install: what the screens said wrong
CI / test (push) Successful in 11m5s

- server init printed every engine's line again on each look while the
  node installed (some 280 lines); each engine's line now once, and again
  only when it changes, as node add does.
- A package install that is no engine's (Slurm's, MariaDB's) read
  ": installing installing mariadb-server, ..."; it is "system
  packages: installing: mariadb-server, ..., with apt-get".
- The slow-judge advice says "ctl model resources JUDGE --cores 4",
  which was refused for want of --memory: cores alone now keep the
  memory as it is.
- server add said both control planes for three.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-11-12 10:38:18 +01:00
1 parent 21828fefce
commit 557a5a1ef3
6 files changed
+88 -10

No files matched your search

+6 -4
View File
@@ -398,7 +398,9 @@ labels:
// checks its own llama.cpp, the CUDA build when it has a GPU, and a new
// machine is often busy with its own package updates first.
client := in.adminAPI()
last := ""
// Each engine's line once, and again only when it changes: the engines'
// states come back together on every look.
seen := map[string]string{}
err = waitFor(ctx, 20*time.Minute, "this node to be ready with an engine", func() (bool, error) {
var nodes []adminapi.NodeView
if err := client.get(ctx, "/api/v1/nodes", &nodes); err != nil {
@@ -412,9 +414,9 @@ labels:
return true, nil
}
for _, p := range n.Provision {
if line := fmt.Sprintf("%s %s: %s %s", p.Engine, p.Version, p.State, p.Detail); line != last {
fmt.Fprintf(in.out, " .. %s\n", strings.TrimSpace(line))
last = line
if line := provisionLine(p.Engine, p.Version, p.State, p.Detail); seen[p.Engine] != line {
fmt.Fprintf(in.out, " .. %s\n", line)
seen[p.Engine] = line
}
// Only llama.cpp is waited for: vLLM installs for minutes after,
// and one this node cannot run is not a reason to stop here.