Quest map
The complete inference engineering roadmap: ten phases from “what’s a KV cache” to a signed offer, with automatically verified milestones along the way. Quests unlock when their prerequisites are at least half done.
Bedrock
The performance mental models and PyTorch fluency everything else builds on. Skimmable if you're strong here — but don't skip Horace He.
Transformer Internals
Build GPT from scratch, then learn the architecture zoo through the serving lens: attention variants, positional encodings, tokenizers, sampling, MoE.
The Inference Engine
KV caching, continuous batching, paged attention, speculative decoding — then the capstone: build your own engine and pass a live OpenAI-conformance probe against it.
The single most important idea in LLM serving.
3 tasks
Continuous batching is why serving companies exist.
4 tasks
Free tokens, provably distribution-preserving.
4 tasks
When the cache can't hold everything, something has to give.
3 tasks
The capstone: a real serving engine, probed live by InferQuest.
4 tasks
GPU Architecture & CUDA
PMPP, the memory hierarchy, occupancy, rooflines, and profiling with Nsight — learn why kernels are fast, and prove yours are.
PMPP + GPU MODE: the canonical on-ramp.
5 tasks
The rite of passage: chase cuBLAS.
3 tasks
Nsight is your microscope; the roofline is your map.
6 tasks
torch.compile is load-bearing in vLLM V1 — stop treating it as magic.
3 tasks
Kernel Engineering
Triton from puzzles to a working flash attention, the FlashAttention lineage, and the modern kernel-library landscape (FlashInfer, CUTLASS, ThunderKittens).
Quantization
From GPTQ/AWQ to the FP8-default, NVFP4/MXFP4 present. Quantize real models with llm-compressor and prove quality with lm-eval.
Production Serving
vLLM V1 and SGLang on your own hardware: deploy, tune, benchmark with real methodology — and pass live conformance and latency probes against your endpoints.
Distributed Inference
TP/PP/EP, disaggregated prefill-decode, KV-cache tiering and transfer, MoE serving at scale, and the Kubernetes layer (llm-d, Gateway API, DRA).
Observability & Economics
Metrics, SLOs, goodput, capacity planning, and cost-per-token from first principles — the part that makes you dangerous in a business conversation.
The Arena
Merged PRs into the engines everyone runs, public benchmarks nobody can argue with, interview gauntlets, and the offer.