Learn Inference
Curated by Learn Inference • Added 2026-07-01
An interactive guide to serving generative AI models in production
Learn Inference is an interactive handbook dedicated to inference engineering: how generative AI models are served at scale, from attention mechanisms and KV caching to paged memory, batching heuristics, and multi-GPU routing.
What You Will Learn
- ✓Inference lifecycle mechanics: prefill vs. decode phases and memory bandwidth bounds
- ✓KV cache footprint calculation, paged allocation strategies, and continuous batching
- ✓Attention kernel optimizations including FlashAttention-2, FlashDecoding, and TensorRT-LLM
- ✓Speculative decoding, model quantization (AWQ, FP8, INT4), and multi-cloud throughput economics
Curator Highlights
- ★Interactive compute and memory simulators
- ★Primary source citations and benchmarks
- ★Sleek, high-craft dark artboard design
Topics & Tags:
Related in AI & Machine Learning
Other vetted resources in this discipline
TrenTorch
AI & Machine Learning•Interactive
Build machine learning frameworks from scratch by hand
Fanout
AI & Machine Learning•Platform
Mapped technical learning across AI research, systems, and ML math
Inference Engineering
AI & Machine Learning•Guide
Deep-dive technical guide to LLM inference optimization & runtime mechanics
