Do not call a GPU shard ready while it computes on the CPU
llama.cpp whose CUDA backend cannot load runs on the CPU without an error. The CUDA build is now asked for its devices when installed, a shard on GPUs must hold memory on each before it is ready, and engine-check reports the devices. Shards get CUDA_DEVICE_ORDER=PCI_BUS_ID so CUDA numbers GPUs as placement does. Refs #2 (item 2). Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
0c7934ba96
commit
057be16a92
13 files changed
+510
-2
No files matched your search
@@ -931,6 +931,14 @@ func (a *Agent) startShard(ctx context.Context, m *llmgwv1.StartShard, out chan<
|
||||
} else {
|
||||
err = a.sup.WaitAlive(ctx, sh)
|
||||
}
|
||||
if err == nil {
|
||||
err = a.onItsGPUs(ctx, eng, spec, sh.Status().PID)
|
||||
if err != nil {
|
||||
// Serving, but not where it was placed: stopped, so the GPU it
|
||||
// holds in the inventory is not taken by a CPU process.
|
||||
_ = a.sup.Stop(ctx, shardID)
|
||||
}
|
||||
}
|
||||
if err != nil {
|
||||
report(supervisor.Failed, err.Error(), sh.Logs(20))
|
||||
return
|
||||
|
||||
Reference in new issue
Block a user