Let the upgrade repair what the field's catalog already holds
tp on a llama.cpp GPU profile is read as gpus_per_node rather than refused, and a Hugging Face repository page as a vLLM source as the repository id, so models written that way are placed after the upgrade instead of dropped from the catalog. Engines adopted after an upgrade are checked for computing on their GPUs too. Refs #2. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
86e9a1cb83
commit
43d7c4eac1
4 files changed
+83
-25
No files matched your search
@@ -314,6 +314,17 @@ func (a *Agent) settleAdopted(sh *supervisor.Shard, o supervisor.Orphan) {
|
||||
"shard", o.ShardID, "replica", o.ReplicaID, "err", err)
|
||||
return
|
||||
}
|
||||
// An engine started by an agent older than the GPU check may be one
|
||||
// serving a GPU placement on the CPU. Stopped, so its replacement starts
|
||||
// through the check and fails there in words, if the build still sees
|
||||
// no GPU — rather than going on unnoticed after the upgrade that could
|
||||
// have caught it.
|
||||
if err := a.onItsGPUs(ctx, eng, o.Spec, sh.Status().PID); err != nil {
|
||||
a.log.Error("stopping an adopted engine that computes on the CPU though placed on GPUs",
|
||||
"shard", o.ShardID, "replica", o.ReplicaID, "err", err)
|
||||
_ = a.sup.Stop(ctx, o.ShardID)
|
||||
return
|
||||
}
|
||||
a.log.Info("adopted engine is serving",
|
||||
"shard", o.ShardID, "replica", o.ReplicaID)
|
||||
}
|
||||
|
||||
Reference in new issue
Block a user