• Batching in LLM Serving Systems
• Faster Causal Self Attention
• GPU Architecture and Programming
• GPU Kernel Programming with Triton and CUDA
• How to write a fast kernel
• InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
• Intro to Mixture of Experts (MoE) in LLM Serving Systems
• Memory Management in LLM Serving Systems
• Modeling and Scaling Performance with Roofline
• Optimizing GPU Kernels
• Parallelism in LLM Serving Systems
• Performance Modeling for LLM Serving Systems
• Practical Lessons from Predicting Clicks on Ads at Facebook
• Quantization in LLM Serving Systems
• Recommender Systems
• Sparsity and Pruning in LLM Serving Systems
• Speculative Decoding in LLM Serving Systems
• Transformer Architecture and Implementation