shreyansh

Index of Inference Engineering

Backend → Inference-Platform track for Java + K8s engineers targeting $75-95k+ offshore-remote (5L/mo net).

Rule: If you can't say why you need Triton, use vLLM.

Theory spine: Inference Engineering by Philip Kiely (Baseten Books, 2026) — 259 pp. Read the chapter per week (see the roadmap); use Appendix A as glossary and Appendix B as the reading list. Framing: every inference platform is runtime + infrastructure + tooling, across the stack from CUDA to Kubernetes.

Related: Index of Pattern Vault · Index of High Level Design · Introduction to Spring Boot

  1. 00 Roadmap and Study Plan

    12 weeks, 45 min/day, 30-50 GPU rent. Start here.

  2. 00b Prerequisites Product and Model Selection

    Ch 0-1: runtime/infra/tooling, online vs offline, model selection, SLOs.

  3. 01 Fundamentals Prefill Decode KV Cache

    Ch 2: roofline, ops:byte, TTFT/TPOT, PagedAttention, continuous batching.

  4. 02 GPU CUDA Basics for Backend Devs

    Ch 3-4.1: VRAM math, bandwidth, arch generations, MIG, NCCL, GPU selection.

  5. 03 vLLM Deep Dive

    Ch 4.2-4.3: serve, EngineArgs, prefix-cache, chunked prefill, /metrics.

  6. 04 SGLang TGI Triton When Why

    Ch 4.3-4.4: decision matrix, when to switch off vLLM (Triton = optional Hopper track).

  7. 05 Quantization AWQ GPTQ FP8

    Ch 5.1: FP16 → FP8 → INT4, parity checks.

  8. 06 Batching Caching Spec Decoding

    Ch 5.2-5.4: batching, RadixAttention, MoE/EP, speculative decoding crossover.

  9. 06b Modalities

    Ch 6: VLM, embeddings, ASR, TTS, image/video generation.

  10. 07 Kubernetes GPU Production

    Ch 7.1-7.3: Deployment+KEDA, prod-stack Helm, probes, PVC cache, multi-cloud/procurement.

  11. 08 Routing Router LiteLLM Dynamo

    Ch 5.5+4.4: round-robin → prefix-aware → disaggregated P/D.

  12. 09 Observability Benchmarking Cost

    Ch 7.4+4.5: Grafana, guidellm/genai-perf, /MTok, publish checklist.

  13. 10 Java Bridge FastAPI Gateway

    Ch 7.5: Spring gateway → vLLM core, minimal Python glue.

  14. 11 Projects P1 P2 P3

    portfolio builds that get interviews.

  15. 12 Interviews Resume Positioning

    positioning as Backend/Platform + Inference.

  16. 13 Resources Glossary

    every link, paper, repo, live benchmark (App A/B mapped).