wfalcon
- Karma
- 0
- Created
- ()
- Submissions
- 0
- LitServe: Build custom AI inference engines (github.com)
- Build your own AI model inference engines (github.com)
- Lightning AI hub: Production AI in your cloud in minutes (lightning.ai)
- Deploy dedicated DeepSeek 32B on L40 GPUs ($8/hour) (lightning.ai)
- Deploy a custom Llama 3 API in 15 lines of code (lightning.ai)
- Remote GPU development with VSCode [video] (youtube.com)
- Reengineering Facebook AI’s deep learning platforms for interoperability (ai.facebook.com)
- Sharded training – How to double the size of PyTorch models (towardsdatascience.com)
- 5-Minute deep dive into multi-GPU training (youtube.com)
- How to Trick a Neural Network (towardsdatascience.com)