Skip to content

Recent Articles

85 posts · sorted by date
June 16, 2026 10 min · read

7/20 - Parallel Decoding: Predicting More Than One Future at a Time

A clear guide to multi-token heads, candidate trees, Medusa-style verification, and the difference between parallel and speculative decoding.

June 15, 2026 10 min · read

6/20 - Early Exit Decoding: Stop Computing Once the Answer Is Clear

How early-exit language models use intermediate layers, confidence, and full-model verification to reduce inference work without hiding quality risk.

June 14, 2026 10 min · read

5/20 - Batch Inference: When Throughput Matters More Than Immediacy

A practical guide to offline LLM batch inference, job design, bucketing, retries, idempotency, cost, and throughput-oriented scheduling.

June 13, 2026 10 min · read

4/20 - PagedAttention: Virtual Memory for the KV Cache

How PagedAttention applies block-based virtual-memory ideas to dynamic KV caches, improving utilization, sharing, and serving throughput.

June 12, 2026 11 min · read

3/20 - FlashAttention: Why Moving Fewer Bytes Beats Doing Fewer FLOPs

An intuitive and rigorous explanation of FlashAttention, tiling, online softmax, IO awareness, exactness, and practical deployment limits.

June 11, 2026 11 min · read

2/20 - Speculative Decoding: Let a Small Model Guess, Let a Large Model Judge

How speculative decoding accelerates autoregressive generation while preserving the target model distribution, with acceptance math and production tradeoffs.

June 10, 2026 20 min · read

1/20 - KV Caching: The Memory That Makes Token Generation Possible

A beginner-friendly and technically deep guide to KV caching, memory sizing, prefix reuse, eviction, isolation, and production metrics.

May 9, 2026 5 min · read

Production LLM Systems Tutorial 1: End-to-End Application Design

A practical tutorial for designing an end-to-end LLM application with gateway, orchestration, retrieval, tools, inference, caching, telemetry, and failure handling.

May 9, 2026 6 min · read

Production LLM Systems Tutorial 2: Latency, Cost, and Quality

A practical tutorial on the latency, cost, and quality trade-offs behind model routing, caching, batching, quantization, speculative decoding, and prompt compression.

May 9, 2026 5 min · read

Production LLM Systems Tutorial 3: Scalable Inference Architecture

A tutorial on scalable LLM inference with vLLM, TensorRT-LLM, SGLang, KV cache management, parallelism, autoscaling, routing, and multi-tenant serving.