Baseten's Philip Kiely Launches Inference Engineering Book, Plus Learning Resources
kmeanskaran · x · 2026-09-06
Philip Kiely of Baseten launched Inference Engineering, distilling four years of production inference work into a book covering the full stack from CUDA to Kubernetes, based on hundreds of thousands of words of docs and interviews with the Baseten engineering team. The post also curates companion resources like 100 Days of LLM Inference, arguing inference is AI's most valuable category and newcomers can become experts quickly.
More from Infra
- Grandma GPUs reborn: 2x Tesla P40 hits 48 tok/s on Qwen 27B via F16 cache + MTP — Jumpy-Operation-4615 · 2026-09-06
- Running H3 across a 3090 and unlocked 64GB CMP 170HX hits OOM in ComfyUI — JustinPooDough · 2026-09-06
- Polygres turns your Postgres into a hybrid search context layer for AI agents — Scobleizer · 2026-09-06
- TCS may invest up to $7.4 billion with TPG in a gigawatt AI campus in Hyderabad — emmanuelvivier · 2026-09-06
- KV cache pressure tool shows vLLM's advertised 2M-token cache can retain 3M after fixes — t4a8945 · 2026-09-06
- Independent Sweep Puts DiffusionGemma Peak Throughput at 3k tok/s, 3x Paper's Claim — bodonoghue85 · 2026-09-06