Multi-GPU programming @GPUMODE

Multi-GPU programming @GPUMODE

Uploaded July 2025 | Updated September 2026, 11 hours ago

Speaker: Markus Hrywniak

Multi-GPU programming

The 4-bitter lesson: Balancing Stability and Performance in NVFP4 RL

Lecture 31: Beginners Guide to Metal

Lecture 81: High-performance purely functional data-parallel array programming

Bonus Lecture: AMD Developer Challenge

PTX/SASS level review

Lecture 111: Spectral Compute: Compile CUDA everywhere

Lecture 94: tvm-ffi

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

Formalized Deep Learning Architectures for Automated Low-Level Kernel Optimization

Lecture 6 Optimizing Optimizers

Lecture 23: Tensor Cores

Multi-GPU programming

🔇 TAP TO UNMUTE