-
Notifications
You must be signed in to change notification settings - Fork 137
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
RAM Misuse on CPU-Only setup / Very Slow #85
Comments
also seeing this when working with ggml quantized LLAMA to 4bit loaded using ctransformers in a ipynb-- when running llama.cpp stuff there is a --mlock parameter to keep the whole model loaded in memory, would be nice to know if that is possible for ctransfomers |
from what I can tell, we would have to add mlock as a parameter when we call |
I will add for text in llm(prompt, stream=True):
print(text, end='', flush=False) |
thank you @marella !! |
Added |
How can i use mmap and mlock when working with langchain and creating the model using CTransformers(path,config) ? No need to reply, found it |
Running on Colab with CPU only works, but I happen to notice that the RAM is not being used. Seems like the library is doing a lot of disk I/O instead of storing the whole model on RAM as happens with the standard GPU setup with hugging face transformers. As a consequence inference is obscenely slow.
I'm trying to hunt down if the issue corresponds directly to llama.cpp, GGML or ctransformers.
Here is the Colab: https://colab.research.google.com/drive/1iGifBXEaXI2JDbJG1Il7BAS8gqVWm8kR?usp=sharing
The text was updated successfully, but these errors were encountered: