Skip to content
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

Add Troubleshooting Section to README #437

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

Dhie-boop
Copy link

This PR enhances the README by adding a Troubleshooting section to help users resolve common issues they may encounter while using DeepSeek-V3.

New Section Added: Troubleshooting
The following issues and solutions are included:

Model weights not found: Instructions on downloading model weights from Hugging Face and placing them correctly.
CUDA errors during inference: Steps to ensure CUDA is set up correctly and PyTorch is configured for GPU use.
Slow inference performance: Recommendations for hardware optimization and using FP8/BF16 modes for faster inference.
Out of memory errors: Guidance on reducing batch sizes or leveraging model parallelism for multi-GPU setups.
Why This Change?
Users may face these common issues when running DeepSeek-V3. Adding a dedicated troubleshooting section improves usability and reduces potential support queries.
The troubleshooting tips are specific to the DeepSeek-V3 workflow and link to external resources for further guidance.

Please let me know if there are additional issues to include or if further edits are required.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant