Skip to content

freshly installed SDXL training problem #546

@xxl2005

Description

@xxl2005

This is for bugs only

Did you already ask in the discord?

No

You verified that this is a bug and not a feature request or question by asking in the discord?

No

Describe the bug

freshly installed sdxl training not working?

OS: CachyOS

GPU: Nvidia 4060 ti

Error Code:

`Running 1 job

Error running job: Failed to import diffusers.models.autoencoders.autoencoder_tiny because of the following error (look up to see its traceback):

/home/tobias/.triton/cache/QLAEYTJR4KV5WSBGJKRUAKVP475DE47NW7P4XMI2RFXBOIE5TZ4Q/cuda_utils.so: undefined symbol: cuModuleGetFunction

Error running on_error: cannot access local variable 'job' where it is not associated with a value

========================================

Result:

  • 0 completed jobs

  • 1 failure

========================================

Traceback (most recent call last):

Traceback (most recent call last):

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/utils/import_utils.py", line 1016, in _get_module

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/utils/import_utils.py", line 1016, in _get_module

    return importlib.import_module("." + module_name, self.__name__)return importlib.import_module("." + module_name, self.__name__)

                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/usr/lib/python3.12/importlib/init.py", line 90, in import_module

File "/usr/lib/python3.12/importlib/init.py", line 90, in import_module

    return _bootstrap._gcd_import(name[level:], package, level)return _bootstrap._gcd_import(name[level:], package, level)

                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "", line 1387, in _gcd_import

File "", line 1387, in _gcd_import

File "", line 1360, in _find_and_load

File "", line 1360, in _find_and_load

File "", line 1310, in _find_and_load_unlocked

File "", line 1310, in _find_and_load_unlocked

File "", line 488, in _call_with_frames_removed

File "", line 488, in _call_with_frames_removed

File "", line 1387, in _gcd_import

File "", line 1387, in _gcd_import

File "", line 1360, in _find_and_load

File "", line 1360, in _find_and_load

File "", line 1331, in _find_and_load_unlocked

File "", line 1331, in _find_and_load_unlocked

File "", line 935, in _load_unlocked

File "", line 935, in _load_unlocked

File "", line 995, in exec_module

File "", line 995, in exec_module

File "", line 488, in _call_with_frames_removed

File "", line 488, in _call_with_frames_removed

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/models/autoencoders/init.py", line 1, in

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/models/autoencoders/init.py", line 1, in

    from .autoencoder_asym_kl import AsymmetricAutoencoderKLfrom .autoencoder_asym_kl import AsymmetricAutoencoderKL

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/models/autoencoders/autoencoder_asym_kl.py", line 22, in

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/models/autoencoders/autoencoder_asym_kl.py", line 22, in

    from ..modeling_utils import ModelMixinfrom ..modeling_utils import ModelMixin

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/models/modeling_utils.py", line 41, in

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/models/modeling_utils.py", line 41, in

    from ..quantizers import DiffusersAutoQuantizer, DiffusersQuantizerfrom ..quantizers import DiffusersAutoQuantizer, DiffusersQuantizer

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/quantizers/init.py", line 16, in

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/quantizers/init.py", line 16, in

    from .auto import DiffusersAutoQuantizerfrom .auto import DiffusersAutoQuantizer

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/quantizers/auto.py", line 22, in

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/quantizers/auto.py", line 22, in

    from .bitsandbytes import BnB4BitDiffusersQuantizer, BnB8BitDiffusersQuantizerfrom .bitsandbytes import BnB4BitDiffusersQuantizer, BnB8BitDiffusersQuantizer

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/quantizers/bitsandbytes/init.py", line 2, in

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/quantizers/bitsandbytes/init.py", line 2, in

    from .utils import dequantize_and_replace, dequantize_bnb_weight, replace_with_bnb_linearfrom .utils import dequantize_and_replace, dequantize_bnb_weight, replace_with_bnb_linear

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/quantizers/bitsandbytes/utils.py", line 32, in

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/quantizers/bitsandbytes/utils.py", line 32, in

    import bitsandbytes as bnbimport bitsandbytes as bnb

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/bitsandbytes/init.py", line 20, in

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/bitsandbytes/init.py", line 20, in

    from .nn import modulesfrom .nn import modules

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/bitsandbytes/nn/init.py", line 21, in

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/bitsandbytes/nn/init.py", line 21, in

    from .triton_based_modules import (from .triton_based_modules import (

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/bitsandbytes/nn/triton_based_modules.py", line 6, in

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/bitsandbytes/nn/triton_based_modules.py", line 6, in

    from bitsandbytes.triton.dequantize_rowwise import dequantize_rowwisefrom bitsandbytes.triton.dequantize_rowwise import dequantize_rowwise

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/bitsandbytes/triton/dequantize_rowwise.py", line 18, in

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/bitsandbytes/triton/dequantize_rowwise.py", line 18, in

    @triton.autotune(@triton.autotune(

      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/runtime/autotuner.py", line 378, in decorator

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/runtime/autotuner.py", line 378, in decorator

    return Autotuner(fn, fn.arg_names, configs, key, reset_to_zero, restore_value, pre_hook=pre_hook,return Autotuner(fn, fn.arg_names, configs, key, reset_to_zero, restore_value, pre_hook=pre_hook,

                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/runtime/autotuner.py", line 130, in init

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/runtime/autotuner.py", line 130, in init

    self.do_bench = driver.active.get_benchmarker()self.do_bench = driver.active.get_benchmarker()

                                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/runtime/driver.py", line 23, in getattr

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/runtime/driver.py", line 23, in getattr

    self._initialize_obj()self._initialize_obj()

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/runtime/driver.py", line 20, in _initialize_obj

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/runtime/driver.py", line 20, in _initialize_obj

    self._obj = self._init_fn()self._obj = self._init_fn()

                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/runtime/driver.py", line 9, in _create_driver

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/runtime/driver.py", line 9, in _create_driver

    return actives[0]()return actives[0]()

                  ^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/backends/nvidia/driver.py", line 535, in init

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/backends/nvidia/driver.py", line 535, in init

    self.utils = CudaUtils()  # TODO: make staticself.utils = CudaUtils()  # TODO: make static

                              ^^^^^^^^^^^^^^^^^^^^^^

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/backends/nvidia/driver.py", line 89, in init

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/backends/nvidia/driver.py", line 89, in init

    mod = compile_module_from_src(Path(os.path.join(dirname, "driver.c")).read_text(), "cuda_utils")mod = compile_module_from_src(Path(os.path.join(dirname, "driver.c")).read_text(), "cuda_utils")

                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/backends/nvidia/driver.py", line 71, in compile_module_from_src

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/triton/backends/nvidia/driver.py", line 71, in compile_module_from_src

    mod = importlib.util.module_from_spec(spec)mod = importlib.util.module_from_spec(spec)

                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

ImportErrorImportError: : /home/tobias/.triton/cache/QLAEYTJR4KV5WSBGJKRUAKVP475DE47NW7P4XMI2RFXBOIE5TZ4Q/cuda_utils.so: undefined symbol: cuModuleGetFunction/home/tobias/.triton/cache/QLAEYTJR4KV5WSBGJKRUAKVP475DE47NW7P4XMI2RFXBOIE5TZ4Q/cuda_utils.so: undefined symbol: cuModuleGetFunction

The above exception was the direct cause of the following exception:

The above exception was the direct cause of the following exception:

Traceback (most recent call last):

Traceback (most recent call last):

File "/home/tobias/AI/ai-toolkit/run.py", line 120, in

File "/home/tobias/AI/ai-toolkit/run.py", line 120, in

    main()main()

File "/home/tobias/AI/ai-toolkit/run.py", line 108, in main

File "/home/tobias/AI/ai-toolkit/run.py", line 108, in main

    raise eraise e

File "/home/tobias/AI/ai-toolkit/run.py", line 95, in main

File "/home/tobias/AI/ai-toolkit/run.py", line 95, in main

    job = get_job(config_file, args.name)job = get_job(config_file, args.name)

                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/tobias/AI/ai-toolkit/toolkit/job.py", line 28, in get_job

File "/home/tobias/AI/ai-toolkit/toolkit/job.py", line 28, in get_job

    from jobs import ExtensionJobfrom jobs import ExtensionJob

File "/home/tobias/AI/ai-toolkit/jobs/init.py", line 1, in

File "/home/tobias/AI/ai-toolkit/jobs/init.py", line 1, in

    from .BaseJob import BaseJobfrom .BaseJob import BaseJob

File "/home/tobias/AI/ai-toolkit/jobs/BaseJob.py", line 5, in

File "/home/tobias/AI/ai-toolkit/jobs/BaseJob.py", line 5, in

    from jobs.process import BaseProcessfrom jobs.process import BaseProcess

File "/home/tobias/AI/ai-toolkit/jobs/process/init.py", line 6, in

File "/home/tobias/AI/ai-toolkit/jobs/process/init.py", line 6, in

    from .TrainVAEProcess import TrainVAEProcessfrom .TrainVAEProcess import TrainVAEProcess

File "/home/tobias/AI/ai-toolkit/jobs/process/TrainVAEProcess.py", line 18, in

File "/home/tobias/AI/ai-toolkit/jobs/process/TrainVAEProcess.py", line 18, in

    from toolkit.image_utils import show_tensorsfrom toolkit.image_utils import show_tensors

File "/home/tobias/AI/ai-toolkit/toolkit/image_utils.py", line 14, in

File "/home/tobias/AI/ai-toolkit/toolkit/image_utils.py", line 14, in

    from diffusers import AutoencoderTinyfrom diffusers import AutoencoderTiny

File "", line 1412, in _handle_fromlist

File "", line 1412, in _handle_fromlist

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/utils/import_utils.py", line 1007, in getattr

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/utils/import_utils.py", line 1007, in getattr

    value = getattr(module, name)value = getattr(module, name)

                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/utils/import_utils.py", line 1006, in getattr

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/utils/import_utils.py", line 1006, in getattr

    module = self._get_module(self._class_to_module[name])module = self._get_module(self._class_to_module[name])

                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/utils/import_utils.py", line 1018, in _get_module

File "/home/tobias/AI/ai-toolkit/venv/lib/python3.12/site-packages/diffusers/utils/import_utils.py", line 1018, in _get_module

    raise RuntimeError(raise RuntimeError(

RuntimeErrorRuntimeError: : Failed to import diffusers.models.autoencoders.autoencoder_tiny because of the following error (look up to see its traceback):

/home/tobias/.triton/cache/QLAEYTJR4KV5WSBGJKRUAKVP475DE47NW7P4XMI2RFXBOIE5TZ4Q/cuda_utils.so: undefined symbol: cuModuleGetFunctionFailed to import diffusers.models.autoencoders.autoencoder_tiny because of the following error (look up to see its traceback):

/home/tobias/.triton/cache/QLAEYTJR4KV5WSBGJKRUAKVP475DE47NW7P4XMI2RFXBOIE5TZ4Q/cuda_utils.so: undefined symbol: cuModuleGetFunction`

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions