Mac: KeyError: 'flags' (dict returned by get_cpu_info does not contain 'flags')

[dfl]

hello, thanks for all your work on this project!

I'm running on a Mac M3, and get_cpu_info() dict does not contain 'flags' key.

>>> from cpuinfo import get_cpu_info
>>> get_cpu_info()
{'python_version': '3.11.7.final.0 (64 bit)', 'cpuinfo_version': [9, 0, 0], 'cpuinfo_version_string': '9.0.0', 'arch': 'ARM_8', 'bits': 64, 'count': 16, 'arch_string_raw': 'arm64', 'brand_raw': 'Apple M3 Max'}

This makes it work:

diff --git a/install_init.py b/install_init.py
index 889c151..024526c 100644
--- a/install_init.py
+++ b/install_init.py
@@ -49,7 +49,7 @@ def get_system_info():

     # Check for AVX2 support
     if importlib.util.find_spec('cpuinfo'):        
-        system_info['avx2'] = 'avx2' in cpuinfo.get_cpu_info()['flags']
+        system_info['avx2'] = 'avx2' in cpuinfo.get_cpu_info().get('flags',[])

[dfl]

PS I also had a dependency error with the latest diffusers, which requires huggingface-hub==0.20.3 (instead of 0.20.1)

[dfl]

one more issue...

Installing llama-cpp-python...
ERROR: llama_cpp_python-0.2.43-macosx_14_0_arm64.whl is not a valid wheel filename.
Traceback (most recent call last):
  File "/Users/dfl/sd/ComfyUI/nodes.py", line 1893, in load_custom_node
    module_spec.loader.exec_module(module)
  File "<frozen importlib._bootstrap_external>", line 940, in exec_module
  File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
  File "/Users/dfl/sd/ComfyUI/custom_nodes/ComfyUI_VLM_nodes/__init__.py", line 30, in <module>
    install_llama(system_info)
  File "/Users/dfl/sd/ComfyUI/custom_nodes/ComfyUI_VLM_nodes/install_init.py", line 93, in install_llama
    install_package("llama-cpp-python", custom_command=custom_command)
  File "/Users/dfl/sd/ComfyUI/custom_nodes/ComfyUI_VLM_nodes/install_init.py", line 73, in install_package
    subprocess.check_call(command)
  File "/opt/homebrew/Cellar/python@3.11/3.11.7_1/Frameworks/Python.framework/Versions/3.11/lib/python3.11/subprocess.py", line 413, in check_call
    raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['/Users/dfl/sd/ComfyUI/venv/bin/python', '-m', 'pip', 'install', 'llama-cpp-python', '--no-cache-dir', 'https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.43/llama_cpp_python-0.2.43-macosx_14_0_arm64.whl']' returned non-zero exit status 1.

Cannot import /Users/dfl/sd/ComfyUI/custom_nodes/ComfyUI_VLM_nodes module for custom nodes: Command '['/Users/dfl/sd/ComfyUI/venv/bin/python', '-m', 'pip', 'install', 'llama-cpp-python', '--no-cache-dir', 'https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.43/llama_cpp_python-0.2.43-macosx_14_0_arm64.whl']' returned non-zero exit status 1.

installing manually worked:

(base) ➜  ComfyUI git:(master) ✗ ./venv/bin/pip install llama-cpp-python
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Collecting llama-cpp-python
  Downloading llama_cpp_python-0.2.43.tar.gz (36.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 36.6/36.6 MB 14.8 MB/s eta 0:00:00
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
  Preparing metadata (pyproject.toml) ... done
Requirement already satisfied: typing-extensions>=4.5.0 in ./venv/lib/python3.11/site-packages (from llama-cpp-python) (4.8.0)
Requirement already satisfied: numpy>=1.20.0 in ./venv/lib/python3.11/site-packages (from llama-cpp-python) (1.24.4)
Requirement already satisfied: diskcache>=5.6.1 in ./venv/lib/python3.11/site-packages (from llama-cpp-python) (5.6.3)
Requirement already satisfied: jinja2>=2.11.3 in ./venv/lib/python3.11/site-packages (from llama-cpp-python) (3.1.2)
Requirement already satisfied: MarkupSafe>=2.0 in ./venv/lib/python3.11/site-packages (from jinja2>=2.11.3->llama-cpp-python) (2.1.3)
Building wheels for collected packages: llama-cpp-python
  Building wheel for llama-cpp-python (pyproject.toml) ... done
  Created wheel for llama-cpp-python: filename=llama_cpp_python-0.2.43-cp311-cp311-macosx_14_0_arm64.whl size=2265033 sha256=afb33ffff14641c2d0da077601821e547400e2b6957060a56727987a9339708e
  Stored in directory: /private/var/folders/71/7jzsfc7x6xx8t1fyzxphfhgh0000gn/T/pip-ephem-wheel-cache-zw0tsmjq/wheels/2a/9d/08/b558eac0caff83868235db10ed76b5b1d2ec06276cdd26dc5d
Successfully built llama-cpp-python
Installing collected packages: llama-cpp-python
Successfully installed llama-cpp-python-0.2.43

[dfl]

and finally: AssertionError: Torch not compiled with CUDA enabled

joytag_patch_for_no_cuda.txt

[gokayfem]

is it working after this changes

[dfl]

yes, after changing CUDA stuff it works 👍🏼On 15 Feb 2024, at 12:28, gokayfem @.***> wrote: is it working after this changes

—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you authored the thread.Message ID: @.***>

[yiwangsimple]

mac m1max ，This node cannot be installed properly. How to deal with it?

[gokayfem]

autogptq library does not support macOS. so i didnt implement other things suggested in this issue for macOS also. i might need to create another branch only for mac. i dont own a mac, i cant quickly iterate on that sorry.

[gokayfem]

mac m1max ，This node cannot be installed properly. How to deal with it?

i created another branch called "mac" and implemented the suggested things in this issue. if you can try to download the mac branch and put in your custom_nodes folder you can use it i think. if you get any error please let me now in this issue.

[yiwangsimple]

mac m1max ，This node cannot be installed properly. How to deal with it?

i created another branch called "mac" and implemented the suggested things in this issue. if you can try to download the mac branch and put in your custom_nodes folder you can use it i think. if you get any error please let me now in this issue.

Great, but I just tried to install it and it still won't import!

[gokayfem]

can you provide me the errors please. i dont have a mac, i cant check it.

[yiwangsimple]

can you provide me the errors please. i dont have a mac, i cant check it.我没有 Mac，无法检查。

Here is the error message from the terminal： Traceback (most recent call last): File "/Users/weiwei/ComfyUI/nodes.py", line 1887, in load_custom_node module_spec.loader.exec_module(module) File "", line 883, in exec_module File "", line 241, in _call_with_frames_removed File "/Users/weiwei/ComfyUI/custom_nodes/ComfyUI_VLM_nodes/init.py", line 29, in system_info = get_system_info() File "/Users/weiwei/ComfyUI/custom_nodes/ComfyUI_VLM_nodes/install_init.py", line 52, in get_system_info system_info['avx2'] = 'avx2' in cpuinfo.get_cpu_info()['flags'] KeyError: 'flags'

Cannot import /Users/weiwei/ComfyUI/custom_nodes/ComfyUI_VLM_nodes module for custom nodes: 'flags'

[gokayfem]

1-) First go to the mac branch

2-) Then download the zip

3-) Delete original VLM nodes

4-)Extract the zip then try to start comfyui again.

[yiwangsimple]

Thanks so much, the install worked with the zip!