2026-05-21T08:43:08.426392334Z 2026-05-21 08:43:08 | INFO     | peft-platform | Remote inference SSH result: code=0, stdout=`torch_dtype` is deprecated! Use `dtype` instead!
2026-05-21T08:43:08.426505308Z [16:42:55.887][MCR][E]mc_device.cpp            :1590: device id 2 or it's subdevice id 2147483647 not exist
2026-05-21T08:43:08.426519286Z [16:42:55.888][MCR][E]mc_runtime_api.cpp       :252 : 2566 : [7f5aac436740] mcSetDevice: Returned mcErrorInvalidDevice
2026-05-21T08:43:08.426528671Z 2026-05-21 16:42:55 | ERROR    | peft-platform | Inference failed: CUDA error: invalid device ordinal
2026-05-21T08:43:08.426540757Z CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
2026-05-21T08:43:08.426553816Z For debugging consider passing CUDA_LAUNCH_BLOCKING=1
2026-05-21T08:43:08.426563717Z Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
2026-05-21T08:43:08.426572356Z 
2026-05-21T08:43:08.426584257Z {"error": "CUDA error: invalid device ordinal\nCUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.\nFor debugging consider passing CUDA_LAUNCH_BLOCKING=1\nCompile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.\n"}, stderr=
