What is Speculative Decoding?
Explains speculative decoding, which pairs a small draft model with a large target model to accelerate LLM inference without changing outputs.
Inference
RLVR vs. the Agent Loop: Training-Time vs. Inference-Time
Distinguishes RLVR as training-time weight updates from inference-time agent verification loops.
Where RL Fits: Training vs. Inference in the LLM Pipeline
Explains that RL in LLMs is a training/alignment stage, not inference, with pipeline context.
Prefix Caching in AI
Explains prefix caching for reusing attention KV computations to speed up shared-prefix AI inference.
LLM Prompt Caching: Implicit vs Explicit
Explains implicit vs explicit LLM prompt caching, prefix constraints, provider support, and when to use each.
Why LLM Caching Is Only for Input Tokens
Explains why LLM prompt caching applies to reusable input-token prefill, not sequential output decoding.