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>
22 lines
654 B
Go
22 lines
654 B
Go
package discovery
|
|
|
|
import (
|
|
"reflect"
|
|
"testing"
|
|
)
|
|
|
|
func TestGPUProcessesAreListedByIndexNotUUID(t *testing.T) {
|
|
gpus := "0, GPU-aaa\n1, GPU-bbb\n2, GPU-ccc\n"
|
|
// Two processes on GPU 1, one on GPU 2, and a GPU this list has never
|
|
// heard of, which is dropped rather than guessed at.
|
|
apps := "GPU-bbb, 4100\nGPU-ccc, 4200\nGPU-bbb, 4300\nGPU-zzz, 9999\n"
|
|
got := parseGPUProcesses(gpus, apps)
|
|
want := map[int][]int{1: {4100, 4300}, 2: {4200}}
|
|
if !reflect.DeepEqual(got, want) {
|
|
t.Errorf("got %v, want %v", got, want)
|
|
}
|
|
if got := parseGPUProcesses(gpus, ""); len(got) != 0 {
|
|
t.Errorf("no compute apps should be no GPU in use: %v", got)
|
|
}
|
|
}
|