Error creating vm context with modules... on RX 580

[Bleach665]

Win 10, Python 3.10.6, Radeon RX 580. Vulkan SDK, runtime installed.
nodai_shark_studio_20240430_1250.exe break with error:

RuntimeError: Error creating vm context with modules: <vm>:0: UNAVAILABLE; none of the executable binaries in the module are supported by the runtime;
[ 0] bytecode compiled_vae.__init:1706 f:\StableDiffusion\nod.ai.SHARK\shark_tmp\vae_decode.torch.tempfile:578:12
      at f:\StableDiffusion\nod.ai.SHARK\shark_tmp\vae_decode.torch.tempfile:252:10

Full output:

f:\StableDiffusion\nod.ai.SHARK>nodai_shark_studio_20240430_1250.exe
vulkan devices are available.
metal devices are not available.
cuda devices are not available.
rocm devices are not available.
local-sync devices are available.
local-task devices are available.
Clearing .mlir temporary files from a prior run. This may take some time...
Clearing .mlir temporary files took 0.0010 seconds.
gradio temporary image cache located at f:\StableDiffusion\nod.ai.SHARK\shark_tmp\gradio. You may change this by setting the GRADIO_TEMP_DIR environment variable.
Clearing gradio UI temporary image files from a prior run. This may take some time...
Clearing gradio UI temporary image files took 0.0000 seconds.
gradio temporary image cache located at f:\StableDiffusion\nod.ai.SHARK\shark_tmp\gradio. You may change this by setting the GRADIO_TEMP_DIR environment variable.
No temporary images files to clear.
diffusers\utils\outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
diffusers\utils\outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
Running on local URL:  http://0.0.0.0:8080

IMPORTANT: You are using gradio version 4.19.2, however version 4.29.0 is available, please upgrade.

--------

IMPORTANT: You are using gradio version 4.19.2, however version 4.29.0 is available, please upgrade.

--------

IMPORTANT: You are using gradio version 4.19.2, however version 4.29.0 is available, please upgrade.

--------


To create a public link, set `share=True` in `launch()`.
To create a public link, set `share=True` in `launch()`.




[LOG] Performing Stable Diffusion Pipeline setup...


[LOG] Initializing new pipeline...

huggingface_hub\file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
Configuring for device:AMD Radeon RX 580 2048SP => vulkan://0

Found vulkan device AMD Radeon RX 580 2048SP. Using target triple rdna2-unknown-windows


[LOG] Pipeline initialized with pipe_id: stabilityai_stable_diffusion_2_1_base_1_77_512x512_fp16_vulkan.


[LOG] Preparing pipeline...


[LOG] Initializing schedulers from model id: stabilityai/stable-diffusion-2-1-base


[LOG] Gathering any pre-compiled artifacts....


[LOG] Tempfile for vae_decode not found. Fetching torch IR...

Saved params to f:\StableDiffusion\nod.ai.SHARK\models\stabilityai_stable_diffusion_2_1_base\vae_decode.safetensors

Configuring for device:vulkan

Found vulkan device AMD Radeon RX 580 2048SP. Using target triple rdna2-unknown-windows

Loading module f:\StableDiffusion\nod.ai.SHARK\models\stabilityai_stable_diffusion_2_1_base_1_77_512x512_fp16_vulkan\vae_decode.vmfb...

        Compiling Vulkan shaders. This may take a few minutes.

Traceback (most recent call last):
  File "C:\Users\Bleach\AppData\Local\Temp\_MEI153402\gradio\queueing.py", line 495, in call_prediction
    output = await route_utils.call_process_api(
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Bleach\AppData\Local\Temp\_MEI153402\gradio\route_utils.py", line 235, in call_process_api
    output = await app.get_blocks().process_api(
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Bleach\AppData\Local\Temp\_MEI153402\gradio\blocks.py", line 1627, in process_api
    result = await self.call_function(
             ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Bleach\AppData\Local\Temp\_MEI153402\gradio\blocks.py", line 1185, in call_function
    prediction = await utils.async_iteration(iterator)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Bleach\AppData\Local\Temp\_MEI153402\gradio\utils.py", line 514, in async_iteration
    return await iterator.__anext__()
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Bleach\AppData\Local\Temp\_MEI153402\gradio\utils.py", line 507, in __anext__
    return await anyio.to_thread.run_sync(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "anyio\to_thread.py", line 56, in run_sync
  File "anyio\_backends\_asyncio.py", line 2144, in run_sync_in_worker_thread
  File "anyio\_backends\_asyncio.py", line 851, in run
  File "C:\Users\Bleach\AppData\Local\Temp\_MEI153402\gradio\utils.py", line 490, in run_sync_iterator_async
    return next(iterator)
           ^^^^^^^^^^^^^^
  File "C:\Users\Bleach\AppData\Local\Temp\_MEI153402\gradio\utils.py", line 673, in gen_wrapper
    response = next(iterator)
               ^^^^^^^^^^^^^^
  File "apps\shark_studio\api\sd.py", line 441, in shark_sd_fn_dict_input
  File "apps\shark_studio\api\sd.py", line 563, in shark_sd_fn
  File "apps\shark_studio\api\sd.py", line 166, in prepare_pipe
  File "apps\shark_studio\modules\pipeline.py", line 63, in get_compiled_map
  File "apps\shark_studio\modules\pipeline.py", line 82, in get_compiled_map
  File "apps\shark_studio\modules\pipeline.py", line 94, in get_compiled_map
  File "shark\iree_utils\compile_utils.py", line 534, in get_iree_compiled_module
    vmfb, config, temp_file_to_unlink = load_vmfb_using_mmap(
                                        ^^^^^^^^^^^^^^^^^^^^^
  File "shark\iree_utils\compile_utils.py", line 484, in load_vmfb_using_mmap
    ctx = ireert.SystemContext(config=config, vm_modules=vm_modules)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "iree\runtime\system_api.py", line 191, in __init__
    self._vm_context = _binding.VmContext(
                       ^^^^^^^^^^^^^^^^^^^
RuntimeError: Error creating vm context with modules: <vm>:0: UNAVAILABLE; none of the executable binaries in the module are supported by the runtime;
[ 0] bytecode compiled_vae.__init:1706 f:\StableDiffusion\nod.ai.SHARK\shark_tmp\vae_decode.torch.tempfile:578:12
      at f:\StableDiffusion\nod.ai.SHARK\shark_tmp\vae_decode.torch.tempfile:252:10

[HerrFrodo]

I have encountered the same error. Did you find a solution?

[Bleach665]

@HerrFrodo , I dont remember(
And cant reproduce now, because migrated to NVidia.