Jun 25, 2026 Modern RL Objectives in Code: Bellman Targets, Trust Regions, PPO Clip, KL Estimators, and LLM Token/Sequence Granularity Apr 20, 2026 From nano-vLLM to vLLM: Scheduler, Paged KV Cache, Prefill/Decode, Tensor Parallelism, and Sampling Mar 16, 2026 Distributed Training for Large Models: Collectives, FSDP/ZeRO, DeviceMesh, and Multi-Dimensional Parallelism Feb 22, 2026 Modern Attention for LLMs: KV Cache, RoPE, MLA, FlashAttention, Sparse/Linear Attention, and MoE Jan 18, 2026 Flow-Based Generative Models: From Normalizing Flows to Flow Matching, Reflow, and MeanFlow