Lecture 1 How to profile CUDA kernels in PyTorch

Lecture 28: Liger Kernel - Efficient Triton Kernels for LLM Training

Lecture 27: gpu.cpp - Portable GPU compute using WebGPU

Lecture 26: SYCL Mode (Intel GPU)

Lecture 25: Speaking Composable Kernel (CK)

Lecture 24: Scan at the Speed of Light

Lecture 23: Tensor Cores

Lecture 22: Hacker's Guide to Speculative Decoding in VLLM

Lecture 21: Scan Algorithm Part 2

Lecture 20: Scan Algorithm

Lecture 19: Data Processing on GPUs

Lecture 18: Fusing Kernels

Lecture 17: NCCL

Lecture 16: On Hands Profiling

Bonus Lecture: CUDA C++ llm.cpp

Lecture 15: CUTLASS

Lecture 14: Practitioners Guide to Triton

Lecture 13: Ring Attention

Lecture 12: Flash Attention

Lecture 11: Sparsity

Lecture 10: Build a Prod Ready CUDA library

Lecture 9 Reductions

Lecture 8: CUDA Performance Checklist

Lecture 7 Advanced Quantization

Lecture 6 Optimizing Optimizers