Tagged: Serving

Articles

• Part 7Cost, Latency & Serving

  Reducing Time to First Token in a Chat App

  Decompose TTFT into network, pre-model work, queueing and prefill, then cut each stage: parallelism, prefix caching, chunked prefill and headroom.

• Part 13Agents & Tool Use

  Guaranteeing Valid JSON Output from LLMs

  Enforce JSON Schema at decode time, design schemas that keep quality high, and add validation, repair and truncation handling on top.

• Part 20Fine-tuning & Adaptation

  Fine-Tuning a Small Model with LoRA on 5,000 Examples

  A practical LoRA recipe for an 8B model on 5K examples: data hygiene, hyperparameters, a real GPU memory budget, and eval-driven checkpoint selection.

• Part 21Cost, Latency & Serving

  Serving Open-Weight LLMs at Scale: Batching, KV Cache, Quantization

  How to size and run an open-weight LLM fleet: prefill vs decode, KV-cache math, continuous batching, FP8/FP4 quantization and goodput per dollar.

• Part 22Production Engineering

  Streaming LLM Responses over SSE and Surviving Disconnects

  Stream tokens with server-sent events, decouple generation from the connection, resume with Last-Event-ID, and cancel cleanly so GPUs are freed.

• Part 25Production Engineering

  Designing a ChatGPT-Style Chat Service for 1M Daily Users

  Back-of-envelope sizing, architecture and overload strategy for an LLM chat product at 1M DAU, where GPUs set both the cost and the latency.