cfregly/ai-performance-engineering
Optimizes GPU training and inference scaling with CUDA and PyTorch
View on index · View in 3D Map
Related repos
- Resources for GPU engineering and AI acceleration
- Optimizes AI inference throughput on GPUs
- CUDA programming course for GPU optimization
- CPU, GPU, and memory profiling for Python with AI-powered optimization tips
- Python notebook environment with GPU compute
- tensor library for machine learning with support for hardware acceleration and model inference
- CUDA kernels, PyTorch notes, LLM blogs, tensor core benchmarks
- Portfolio optimization with 160x speedups via NVIDIA GPUs
- open-source reimplementation of Google’s TensorProcessing Unit by UC Santa Barbara ArchLab
- Framework for execution environments for reinforcement learning training
