Optimizing LLM Training and Inference Performance on GPUs (Workshop) – Faradawn Yang Blog 25/06/2026 · 0 Comment Optimizing LLM Training and Inference Performance on GPUs (Workshop) - Faradawn YangOptimizing LLM Training on GPUsAI Optimization Lecture 01 - Prefill vs Decode - Mastering LLM Techniques from NVIDIAMastering LLM Inference Optimization From Theory to Cost Effective Deployment: Mark MoyouLLM Inference Optimization Explained | Quantization, KV Cache, Batching & GPU PerformanceFleet: Optimizing LLM Inference on Chiplet GPUsFaster LLMs: Accelerate Inference with Speculative DecodingUnlocking LLM Performance with EBPF: Optimizing Training and Inference Pipelines - Yang XiangLLM Inference OptimizationLLM Inference Lecture: Roofline Analysis for GPU (arithmetic intensity, compute and memory bound)12
