deepseek-v3
https://github.com/deepseek-ai/deepseek-v3
Python
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to deepseek-v3
Help out
- Issues
- Fix: safer and cleaner forward() in distributed embedding layer
- Improve convert.py with error handling and code optimization
- Create Thunder
- 沈耀888π × DeepSeek-V4 診斷報告書 Shen-Yao 888π × DeepSeek V4 Diagnostic Statement
- Add Troubleshooting Section to README
- Optimize Multi-head Latent Attention (MLA) with Fast Path for Short Sequences
- Critical Improvements for Model Correctness, Efficiency, and Robustness
- [BUG]死循环
- [Feature Request] Adaptive-K Routing Support for Dynamic Expert Selection
- Optimizing
- Docs
- Python not yet supported