localGPT icon indicating copy to clipboard operation
localGPT copied to clipboard
verified publisher icon PromtEngineer

Error on run_localGPT.py --device_type mps

Open Fluxkom opened this issue 2 years ago • 6 comments

Enter a query: Tell me about Orcas ggml_metal_graph_compute: command buffer 0 failed with status 5 GGML_ASSERT: /private/var/folders/qs/yhqls5xn3c3fdg5tl00tzfnm0000gn/T/pip-install-ulcd5sl7/llama-cpp-python_3c33c62f26e243acb2c2fa6c61e5606d/vendor/llama.cpp/ggml-metal.m:1185: false zsh: abort python run_localGPT.py --device_type mps stefan@MBFVFFG677Q05G localGPT % /Users/stefan/.pyenv/versions/3.10.13/lib/python3.10/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 '

It seems to try to run the gguf model with ggml settings

Fluxkom avatar Oct 24 '23 14:10 Fluxkom

Same error after using updated API and latest code.

TechInnovate01 avatar Nov 30 '23 09:11 TechInnovate01

I have the same problem, I use the M1 chip

CanCanNeed-pro avatar Dec 20 '23 07:12 CanCanNeed-pro

Im facing the same issue..the exact error cant be understood

Advik29 avatar Dec 20 '23 19:12 Advik29

Same problem here.

Anyone have been able to work this out? Thanks!

gregorioosorio avatar Feb 05 '24 01:02 gregorioosorio

Same here with same M1 setup

arioboo avatar Mar 01 '24 13:03 arioboo

Same issue here with M1 setup

machineska avatar Mar 29 '24 22:03 machineska