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:
1 parent
f285aa0548
commit
0bd0d881c5
15 files changed
+517
-126
No files matched your search
@@ -36,6 +36,8 @@ type StatusSink interface {
|
||||
// still starting, and treating each report as a state change would reset
|
||||
// the timers that decide when a slow start has become a failed one.
|
||||
OnFetchProgress(replicaID, shardID, source string, done, total int64)
|
||||
// OnShardCompute records where a shard's engine said it runs the model.
|
||||
OnShardCompute(replicaID, shardID string, c reconciler.Compute)
|
||||
Adopt(nodeID string, shards []reconciler.AdoptedShard) (unclaimed []reconciler.AdoptedShard)
|
||||
}
|
||||
|
||||
@@ -449,6 +451,12 @@ func (s *Service) handle(nodeID string, msg *llmgwv1.AgentMessage) {
|
||||
}
|
||||
st := StateFromWire(m.Shard.GetState())
|
||||
s.status.OnShardStatus(m.Shard.GetReplicaId(), m.Shard.GetShardId(), st, m.Shard.GetError())
|
||||
if c := m.Shard.GetCompute(); c != nil {
|
||||
s.status.OnShardCompute(m.Shard.GetReplicaId(), m.Shard.GetShardId(), reconciler.Compute{
|
||||
Backend: c.GetBackend(), Devices: c.GetDevices(),
|
||||
Offloaded: int(c.GetLayersOffloaded()), Total: int(c.GetLayersTotal()),
|
||||
})
|
||||
}
|
||||
if m.Shard.GetState() == llmgwv1.ShardStatus_STATE_FAILED {
|
||||
s.log.Error("shard failed",
|
||||
"node", nodeID, "shard", m.Shard.GetShardId(),
|
||||
|
||||
Reference in new issue
Block a user