-
Notifications
You must be signed in to change notification settings - Fork 10.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
unsupported op 'MUL_MAT' #4998
Comments
I encountered the same problem |
Likely your device is missing Show the logs of
|
yep, that value is set to false:
is there any fix? |
Same problem on Macbook Pro 2018 16GB (Intel, AMD Radeon Pro 555X) ggml_metal_graph_compute_block_invoke: error: unsupported op 'MUL_MAT' also: |
The only way is to implement the respective Metal kernels without using If somebody implements the kernels, we can put them in |
From what i understood, this error occurs due to the fact that all this is running on gpu. This may seem dumb but how do i run llama.cpp on the cpu instead? |
Most of the examples support |
This worked for me, thank you! I was running llama-2-7b-chat.Q4_K_M on my macbook pro 2016 (8G DRAM), and got an error said: It was running successfully right now, but very slow, almost take 2~3min to predict each word. I could see very high IO load via iostat command and also the cpu-sys was high too, which means it was trying to swap data between disk and memory. Conclusion: I need a new macbook definitely! |
This issue is stale because it has been open for 30 days with no activity. |
This issue was closed because it has been inactive for 14 days since being marked as stale. |
passing param -ngl 0 param solved the problem. |
This used to help be on my mid 2015 macbook, but no more 😢 |
system: Mac Book Air (intel)
Happens when i try to run phi-2
The text was updated successfully, but these errors were encountered: