Skip to content

Recent Articles

85 posts · sorted by date
June 25, 2026 10 min · read

16/20 - Streaming Generation: The First Token Is a Product Decision

How to design token streaming from model to browser with SSE or gRPC, buffering, cancellation, backpressure, usage accounting, and terminal events.

June 24, 2026 10 min · read

15/20 - Memory Offloading: Trading Bandwidth for Capacity

A systems guide to moving weights and KV cache between GPU, CPU, and NVMe, including prefetch, pinning, overlap, and latency tradeoffs.

June 23, 2026 10 min · read

14/20 - Dynamic Batching: Waiting Microseconds to Save Milliseconds

How dynamic batchers collect live requests, select batch sizes, manage queue delay, priorities, shapes, and throughput-latency tradeoffs.

June 22, 2026 10 min · read

13/20 - Graph Optimization: Teaching ONNX and TensorRT to See the Whole Model

How constant folding, node elimination, fusion, layout selection, precision propagation, and engine building optimize inference graphs.

June 21, 2026 10 min · read

12/20 - Sequence Parallelism: Divide the Tokens, Not the Meaning

A careful guide to sequence parallelism, its relationship to tensor and context parallelism, communication patterns, and long-context inference.

June 20, 2026 10 min · read

11/20 - Pipeline Parallelism: Turning Model Depth into an Assembly Line

How pipeline parallelism splits transformer layers across GPUs, where pipeline bubbles come from, and when it helps or hurts LLM inference.

June 19, 2026 10 min · read

10/20 - Tensor Parallelism: Splitting One Layer Across Many GPUs

A rigorous but approachable guide to column and row tensor parallelism, collectives, topology, latency, and production sizing for LLM inference.

June 18, 2026 10 min · read

9/20 - Quantized Kernels: Why a 4-Bit Model Is Not Automatically Fast

How packing, dequantization, scaling, fused GEMM, group size, and hardware support determine whether quantized LLMs deliver real speedups.

June 17, 2026 10 min · read

8/20 - Mixed Precision Inference: Spend Bits Where They Matter

A practical mental model for FP32, BF16, FP16, FP8, FP4, accumulation precision, scaling, calibration, and mixed-precision validation.

June 16, 2026 10 min · read

The Human Control Plane: What a VP Operations Must Build in an AI Company

A practical operating guide for the VP Operations role in an AI company: cadence, metrics, talent, cost discipline, customer trust, governance, and execution at speed.