Skip to content

[bug]: AMD RYZEN AI MAX+ 395 w/ Radeon 8060S not supported #8023

Open
@marcushoff

Description

@marcushoff

Is there an existing issue for this problem?

  • I have searched the existing issues

Operating system

Linux

GPU vendor

AMD (ROCm)

GPU model

AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

GPU VRAM

96GB

Version number

5.12.0rc1

Browser

Brave

Python dependencies

{
    "version": "5.12.0rc1", 
    "dependencies": {
        "accelerate"  : "1.7.0"         , 
        "compel"      : "2.0.2"         , 
        "cuda"        : null            , 
        "diffusers"   : "0.33.0"        , 
        "numpy"       : "1.26.3"        , 
        "opencv"      : "4.9.0.80"      , 
        "onnx"        : "1.16.1"        , 
        "pillow"      : "11.0.0"        , 
        "python"      : "3.12.9"        , 
        "torch"       : "2.7.0+rocm6.3" , 
        "torchvision" : "0.22.0+rocm6.3", 
        "transformers": "4.51.3"        , 
        "xformers"    : null              
    }, 
    "config": {
        "schema_version": "4.0.2", 
        "legacy_models_yaml_path": null, 
        "host": "127.0.0.1", 
        "port": 9090, 
        "allow_origins": [], 
        "allow_credentials": true, 
        "allow_methods": ["*"], 
        "allow_headers": ["*"], 
        "ssl_certfile": null, 
        "ssl_keyfile": null, 
        "log_tokenization": false, 
        "patchmatch": true, 
        "models_dir": "models", 
        "convert_cache_dir": "models/.convert_cache", 
        "download_cache_dir": "models/.download_cache", 
        "legacy_conf_dir": "configs", 
        "db_dir": "databases", 
        "outputs_dir": "outputs", 
        "custom_nodes_dir": "nodes", 
        "style_presets_dir": "style_presets", 
        "workflow_thumbnails_dir": "workflow_thumbnails", 
        "log_handlers": ["console"], 
        "log_format": "color", 
        "log_level": "info", 
        "log_sql": false, 
        "log_level_network": "warning", 
        "use_memory_db": false, 
        "dev_reload": false, 
        "profile_graphs": false, 
        "profile_prefix": null, 
        "profiles_dir": "profiles", 
        "max_cache_ram_gb": null, 
        "max_cache_vram_gb": null, 
        "log_memory_usage": false, 
        "device_working_mem_gb": 3, 
        "enable_partial_loading": false, 
        "keep_ram_copy_of_weights": true, 
        "ram": null, 
        "vram": null, 
        "lazy_offload": true, 
        "pytorch_cuda_alloc_conf": null, 
        "device": "auto", 
        "precision": "auto", 
        "sequential_guidance": false, 
        "attention_type": "auto", 
        "attention_slice_size": "auto", 
        "force_tiled_decode": false, 
        "pil_compress_level": 1, 
        "max_queue_size": 10000, 
        "clear_queue_on_startup": false, 
        "allow_nodes": null, 
        "deny_nodes": null, 
        "node_cache_size": 512, 
        "hashing_algorithm": "blake3_single", 
        "remote_api_tokens": null, 
        "scan_models_on_startup": false
    }, 
    "set_config_fields": ["legacy_models_yaml_path"]
}

What happened

Error on launch and error on image generation.

Starting up...
Preparing first run of this install - may take a minute or two...
Started Invoke process with PID: 60646
[2025-05-20 12:03:35,390]::[InvokeAI]::INFO --> Using torch device: AMD Radeon Graphics
Could not load bitsandbytes native library: 'NoneType' object has no attribute 'split'
Traceback (most recent call last):
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/bitsandbytes/cextension.py", line 85, in <module>
    lib = get_native_library()
          ^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/bitsandbytes/cextension.py", line 64, in get_native_library
    cuda_specs = get_cuda_specs()
                 ^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/bitsandbytes/cuda_specs.py", line 39, in get_cuda_specs
    cuda_version_string=(get_cuda_version_string()),
                         ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/bitsandbytes/cuda_specs.py", line 29, in get_cuda_version_string
    major, minor = get_cuda_version_tuple()
                   ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/bitsandbytes/cuda_specs.py", line 24, in get_cuda_version_tuple
    major, minor = map(int, torch.version.cuda.split("."))
                            ^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'split'
CUDA Setup failed despite CUDA being available. Please run the following command to get more information:
python -m bitsandbytes
Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
and open an issue at: https://github.com/bitsandbytes-foundation/bitsandbytes/issues
[2025-05-20 12:03:37,389]::[InvokeAI]::INFO --> cuDNN version: 3003000
[2025-05-20 12:03:39,613]::[InvokeAI]::INFO --> Patchmatch initialized
[2025-05-20 12:03:40,132]::[InvokeAI]::INFO --> InvokeAI version 5.12.0rc1
[2025-05-20 12:03:40,132]::[InvokeAI]::INFO --> Root directory = /home/mho/invokeai
[2025-05-20 12:03:40,133]::[InvokeAI]::INFO --> Initializing database at /home/mho/invokeai/databases/invokeai.db
[2025-05-20 12:03:40,136]::[InvokeAI]::INFO --> Database update needed
[2025-05-20 12:03:40,136]::[InvokeAI]::INFO --> Backing up database to /home/mho/invokeai/databases/invokeai_backup_20250520-120340.db
[2025-05-20 12:03:40,145]::[InvokeAI]::INFO --> Database updated successfully
[2025-05-20 12:03:40,147]::[ModelManagerService]::INFO --> [MODEL CACHE] Calculated model RAM cache size: 60897.80 MB. Heuristics applied: [1, 2].
[2025-05-20 12:03:40,153]::[InvokeAI]::INFO --> Pruned 1 finished queue items
[2025-05-20 12:03:40,179]::[InvokeAI]::INFO --> Invoke running on http://127.0.0.1:9090/ (Press CTRL+C to quit)
[2025-05-20 12:03:51,287]::[InvokeAI]::INFO --> Executing queue item 7, session 6b5299d0-0d7a-4cc5-ac18-51a91ca055cb
[2025-05-20 12:03:51,828]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model '26d526b6-fd71-45d3-874d-3aa7b3ca57c2:text_encoder' (CLIPTextModel) onto cuda device in 0.37s. Total model size: 234.72MB, VRAM: 234.72MB (100.0%)
[2025-05-20 12:03:51,878]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model '26d526b6-fd71-45d3-874d-3aa7b3ca57c2:tokenizer' (CLIPTokenizer) onto cuda device in 0.00s. Total model size: 0.00MB, VRAM: 0.00MB (0.0%)
[2025-05-20 12:03:51,959]::[InvokeAI]::ERROR --> Error while invoking session 6b5299d0-0d7a-4cc5-ac18-51a91ca055cb, invocation d44433b7-d383-4bc8-b635-ee04e9ae73e0 (sdxl_compel_prompt): HIP error: invalid device function
HIP kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing AMD_SERIALIZE_KERNEL=3
Compile with `TORCH_USE_HIP_DSA` to enable device-side assertions.
[2025-05-20 12:03:51,959]::[InvokeAI]::ERROR --> Traceback (most recent call last):
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/invokeai/app/services/session_processor/session_processor_default.py", line 129, in run_node
    output = invocation.invoke_internal(context=context, services=self._services)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/invokeai/app/invocations/baseinvocation.py", line 241, in invoke_internal
    output = self.invoke(context)
             ^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/invokeai/app/invocations/compel.py", line 268, in invoke
    c1, c1_pooled = self.run_clip_compel(context, self.clip, self.prompt, False, "lora_te1_", zero_on_empty=True)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/invokeai/app/invocations/compel.py", line 217, in run_clip_compel
    c, _options = compel.build_conditioning_tensor_for_conjunction(conjunction)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/compel/compel.py", line 186, in build_conditioning_tensor_for_conjunction
    this_conditioning, this_options = self.build_conditioning_tensor_for_prompt_object(p)
                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/compel/compel.py", line 218, in build_conditioning_tensor_for_prompt_object
    return self._get_conditioning_for_flattened_prompt(prompt), {}
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/compel/compel.py", line 282, in _get_conditioning_for_flattened_prompt
    return self.conditioning_provider.get_embeddings_for_weighted_prompt_fragments(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/compel/embeddings_provider.py", line 120, in get_embeddings_for_weighted_prompt_fragments
    base_embedding = self.build_weighted_embedding_tensor(tokens, per_token_weights, mask, device=device)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/compel/embeddings_provider.py", line 357, in build_weighted_embedding_tensor
    empty_z = self._encode_token_ids_to_embeddings(empty_token_ids)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/compel/embeddings_provider.py", line 390, in _encode_token_ids_to_embeddings
    text_encoder_output = self.text_encoder(token_ids,
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/transformers/utils/generic.py", line 965, in wrapper
    output = func(self, *args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/transformers/models/clip/modeling_clip.py", line 1049, in forward
    return self.text_model(
           ^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/transformers/utils/generic.py", line 965, in wrapper
    output = func(self, *args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/transformers/models/clip/modeling_clip.py", line 945, in forward
    hidden_states = self.embeddings(input_ids=input_ids, position_ids=position_ids)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/transformers/models/clip/modeling_clip.py", line 292, in forward
    inputs_embeds = self.token_embedding(input_ids)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/invokeai/backend/model_manager/load/model_cache/torch_module_autocast/custom_modules/custom_embedding.py", line 29, in forward
    return super().forward(input)
           ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/torch/nn/modules/sparse.py", line 190, in forward
    return F.embedding(
           ^^^^^^^^^^^^
  File "/home/mho/invokeai/.venv/lib/python3.12/site-packages/torch/nn/functional.py", line 2551, in embedding
    return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: HIP error: invalid device function
HIP kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing AMD_SERIALIZE_KERNEL=3
Compile with `TORCH_USE_HIP_DSA` to enable device-side assertions.
[2025-05-20 12:03:51,981]::[InvokeAI]::INFO --> Graph stats: 6b5299d0-0d7a-4cc5-ac18-51a91ca055cb
                          Node   Calls   Seconds  VRAM Used
             sdxl_model_loader       1    0.005s     0.000G
            sdxl_compel_prompt       1    0.653s     0.236G
TOTAL GRAPH EXECUTION TIME:   0.658s
TOTAL GRAPH WALL TIME:   0.659s
RAM used by InvokeAI process: 1.81G (+0.395G)
RAM used to load models: 0.23G
VRAM in use: 0.236G
RAM cache statistics:
   Model cache hits: 2
   Model cache misses: 2
   Models cached: 2
   Models cleared from cache: 0
   Cache high water mark: 0.23/0.00G
Shutting down...
[2025-05-20 12:04:10,156]::[ModelInstallService]::INFO --> Installer thread 126389474817728 exiting
Process exited with signal SIGTERM

We'll activate the virtual environment for the install at /home/mho/invokeai.

What you expected to happen

No errors.
Image generated.

How to reproduce the problem

Run invoke on computer with AMD RYZEN AI MAX+ 395 w/ Radeon 8060S (gfx1151)

Additional context

No response

Discord username

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions