{{ message }}
Repository navigation
macOS 15.0 (24A335) M1 buffer is not large enough and resource_tracker: There appear to be %d #107
Description
I'm not sure if this question is appropriate to ask here, I'm not a professional programmer, if anyone is willing to offer help and guidance, I would be very grateful.
Two weeks ago, I started using the GGUF model, and it can work normally. Today, I upgraded the system of the MacBook pro m1 computer to the latest version of macOS 15.0 (24A335). An error prompt occurred when running GGUF workflow in comfyUI:
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
- Avoid using `tokenizers` before the fork if possible
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
/AppleInternal/Library/BuildRoots/5a8a3fcc-55cb-11ef-848e-8a553ba56670/Library/Caches/com.apple.xbs/Sources/MetalPerformanceShaders/MPSCore/Types/MPSNDArray.mm:891: failed assertion `[MPSNDArray, initWithBufferImpl:offset:descriptor:isForNDArrayAlias:isUserBuffer:] Error: buffer is not large enough. Must be 63700992 bytes
'/Users/***/lib/python3.11/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d '
My system information：
Python version: 3.11.5 (main, Sep 11 2023, 08:31:25) [Clang 14.0.6 ]
pytorch version: 2.6.0.dev20240916
ComfyUI Revision: 2701 [7183fd16] | Released on '2024-09-17'
I didn't know if this is related to updating the system.
thx
Activity
city96 commentedon Sep 17, 2024
Could you test with the FP16/FP8 model and the default nodes w/o the custom node pack? Might be more appropriate for the ComfyUI repo if it still happens with those since the error makes it sound like it's not a problem with this node pack, I could be wrong though.
Also makes it sound like you can set the env variable
export TOKENIZERS_PARALLELISM=falseto possibly fix it? Might be worth testing.guoreex commentedon Sep 17, 2024
Thank you for your reply.
My computer only has 16G ram, which is not enough to run the FP8 model.
set export TOKENIZERS_PARALLELISM=false There are still mistakes：
The error occurs after starting the generation calculation.
city96 commentedon Sep 17, 2024
Well, at least there's a progress bar now lol, buffer error is still there though...
I don't have any apple device to test on, but looks like there's a similar issue on the pytorch tracker with a linked PR, not sure if the cause is the same though. Might be worth keeping an eye on and testing on latest nightly once it gets merged? pytorch/pytorch#136132
tombearx commentedon Sep 23, 2024
Still have the issue using today's nightly build. Any one else?
thenabytes commentedon Sep 23, 2024
M2 Macbook Air, 16GB RAM
Sequoia 15.0
Python version: 3.12.6 (main, Sep 6 2024, 19:03:47) [Clang 15.0.0 (clang-1500.3.9.4)]
pytorch version: 2.6.0.dev20240923
ComfyUI Revision: 2724 [3a0eeee3] | Released on '2024-09-23'
jonny7737 commentedon Sep 25, 2024
M2 Max Mac Studio, 64GB RAM
Sequoia 15.0
Python 3.11.9
Only when running GGUF models (fp16 fp8 work fine)
/AppleInternal/Library/BuildRoots/5a8a3fcc-55cb-11ef-848e-8a553ba56670/Library/Caches/com.apple.xbs/Sources/MetalPerformanceShaders/MPSCore/Types/MPSNDArray.mm:891: failed assertion `[MPSNDArray, initWithBufferImpl:offset:descriptor:isForNDArrayAlias:isUserBuffer:] Error: buffer is not large enough. Must be 77856768 bytes
<<Slight correction: flux1-dev-Q8_0.GGUF WORKS!!>>
Correcting the correction: Q8 does not work (working test was before Sequoia)
tombearx commentedon Sep 26, 2024
Does Q8 work? What PyTorch version are you using?
jonny7737 commentedon Sep 26, 2024
I just retested Q8 and it does not work :( Working test was before Sequoia. Sorry for the false hope.
jonny7737 commentedon Sep 27, 2024
This is the only GGUF that I have found to work since Sequoia update:
https://huggingface.co/city96/FLUX.1-dev-gguf/blob/main/flux1-dev-F16.gguf
tombearx commentedon Sep 30, 2024
Guys, I've tested torch==2.4.1 and it works for gguf Q8.
jonny7737 commentedon Sep 30, 2024
What is the mac config for your test?
M? xxGB
Can't install pytorch==2.4.1 because it requires python < 3.9
tombearx commentedon Sep 30, 2024
Strange, I use python 3.11.
M1 Max, 32gb
jonny7737 commentedon Sep 30, 2024
I use 3.11 as well but the install of torch 2.4.1 failed due to python version.
Very strange. I'll try again.
Thanks.
bauerwer commentedon Sep 30, 2024
Same issue here, flux GGUF's bail out with a mem allocation error in MPS (Error: buffer is not large enough. Must be 77856768 bytes). Worked on Mac OS 14.x but not anymore on Mac OS 15.x. same issue with torch 2.4.1 and 2.6.0.dev20240924 (nightly from last week).
As reference and as I can run heavier flux (M3 Max, 128GB RAM), the direct flux models work fine. Would love to run GGUFs though due to less RAM and speed.
jonny7737 commentedon Oct 1, 2024
FINALLY!!!
After 6 tries to get pytorch 2.4.1 to install, the install completed successfully.
A simple test with a Q5 GGUF model and it did not abort comfyui.
But, the image generated at an absolutely appauling 45 seconds per iteration.
It works but is not usable.
cchance27 commentedon Oct 11, 2024
Thers something going on with every nightly build thats the issue for some reason the 2.6 nightlies all break the GGUF code for some reason running 32gb that works fine with Q8 on 2.4.1 fails every time with this semaphore error when moved to nightly.
I can't say if its seqouia + 2.6 nightlies but can confirm sequoia + 2.4.1 + gguf works fine, sequoia + 2.6 + gguf bails every time
This is super annoying because the 2.6 nightly finally added support for autocast on MPS
craii commentedon Oct 12, 2024
thank you bro! By using pytorch 2.4.1, It works again!
craii commentedon Oct 12, 2024
@city96
Hello Bro. I think this could be added to readme as a temporary fix guide.
city96 commentedon Oct 15, 2024
@craii Added it under the installation section w/ a link to this issue thread.
cchance27 commentedon Oct 15, 2024
Just so you know i haven't tested them all Q8_0 on M3 and torch 2.4.1 i get ~16-17s/it ... on Q5 and Q8_4 (i've been playing with custom quants) and they are 40-50s/it its insane not sure why it's so bad, but ya, Q8_0 loads and runs fastest so far.
Vargol commentedon Oct 15, 2024
Q8 is faster because it can run fully on the GPU units, the others use a shift function that has to fallback to running on the CPU.
For example if Comfy is not hiding it in the terminal you should something see this
when using the other models, this was taken from a Q6_K run in InvokeAI.
jack813 commentedon Oct 21, 2024
After Ptorch nightly 2.6.0 dev20241020 version, the problem has been fixed. I can run GGUF's quantized Flux.1 Dev Q4_0 version on my Mac book m1 Pro Memory: 16GB
jonny7737 commentedon Oct 21, 2024
jonny7737 commentedon Oct 21, 2024
M2 Max 64GB after installing the 241020 nightly, GGUF seems to work again. Thanks for the heads up.
jeanjerome commentedon Oct 21, 2024
I also managed to get a GGUF working with
pytorch 2.6.0.dev20241020 py3.10_0 pytorch-nightlyonSequoia 15.0.1.ReZeroS commentedon Oct 25, 2024
conda install pytorch-nightly::pytorch torchvision torchaudio -c pytorch-nightly
jeanjerome commentedon Oct 25, 2024
Or simply
conda install pytorch torchvision torchaudio -c pytorch-nightly(https://developer.apple.com/metal/pytorch/)craii commentedon Oct 25, 2024
M3 24GB works properly on Q4 schnell model after pytorch dev-20241020-nightly installed. But it seems to consume much more memory when given the same parameters to generate pictures(Now it takes 25
29gb while only 1720gb was taken before)cchance27 commentedon Oct 25, 2024
Just use 2.4.1 not nightly, report the regression to PyTorch team they already fixed some of the other regressions