What a replica computes on comes from nvidia-smi; llama.cpp says its layers only at -lv 4
Checked against the installed llama.cpp (b10991): at its default verbosity it prints neither the devices it uses nor the layers it offloads, so the start-up output said nothing and every replica's ON column stayed empty. The agent now takes compute from nvidia-smi - the GPUs the shard's processes hold memory on, and how much - or CPU, for every engine, falling back to it when llama.cpp's output says nothing; adopted engines get it too, and each session reports it once per shard as a compute-only status. engine-check runs its GPU token at -lv 4, where llama.cpp does say where its layers went. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
25b3e129fe
commit
b5d650af16
7 files changed
+147
-13
No files matched your search
@@ -449,14 +449,18 @@ func (s *Service) handle(nodeID string, msg *llmgwv1.AgentMessage) {
|
||||
f.GetSource(), f.GetBytesDone(), f.GetBytesTotal())
|
||||
return
|
||||
}
|
||||
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()),
|
||||
})
|
||||
// Compute alone, with no state: not a transition.
|
||||
if m.Shard.GetState() == llmgwv1.ShardStatus_STATE_UNSPECIFIED {
|
||||
return
|
||||
}
|
||||
}
|
||||
st := StateFromWire(m.Shard.GetState())
|
||||
s.status.OnShardStatus(m.Shard.GetReplicaId(), m.Shard.GetShardId(), st, m.Shard.GetError())
|
||||
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