|
|
@ -2,8 +2,8 @@
|
|
|
|
Description=Petals Inference
|
|
|
|
Description=Petals Inference
|
|
|
|
|
|
|
|
|
|
|
|
[Service]
|
|
|
|
[Service]
|
|
|
|
#User=petals
|
|
|
|
User=petals
|
|
|
|
#Group=petals
|
|
|
|
Group=petals
|
|
|
|
Environment=PJRT_DEVICE=TPU
|
|
|
|
Environment=PJRT_DEVICE=TPU
|
|
|
|
ExecStart=/home/petals/venv/bin/python -m petals.cli.run_server --port 31330 petals-team/StableBeluga2 --device xla --num_blocks=4
|
|
|
|
ExecStart=/home/petals/venv/bin/python -m petals.cli.run_server --port 31330 petals-team/StableBeluga2 --device xla --num_blocks=4
|
|
|
|
|
|
|
|
|
|
|
|