Skip to content

Recent Articles

85 posts · sorted by date
July 6, 2026 10 min · read

6/21 - The Serving Layer: Triton, vLLM, KServe, Ray Serve, and SGLang

A production-focused guide to the serving layer: triton, vllm, kserve, ray serve, and sglang, with architecture, capacity math, failure analysis, and operational controls.

July 5, 2026 10 min · read

5/21 - Training Across the Fleet: DDP, FSDP, DeepSpeed, and ZeRO

A production-focused guide to training across the fleet: ddp, fsdp, deepspeed, and zero, with architecture, capacity math, failure analysis, and operational controls.

July 4, 2026 10 min · read

4/21 - The Memory of a Conversation: KV, Prefix Reuse, Speculation, and Throughput

A production-focused guide to the memory of a conversation: kv, prefix reuse, speculation, and throughput, with architecture, capacity math, failure analysis, and operational controls.

July 3, 2026 10 min · read

3/21 - The Inference Engine Room: vLLM, TensorRT-LLM, SGLang, and llama.cpp

A production-focused guide to the inference engine room: vllm, tensorrt-llm, sglang, and llama.cpp, with architecture, capacity math, failure analysis, and operational controls.

July 2, 2026 11 min · read

2/21 - Smaller Numbers, Faster Models: Quantization and Batching

How INT8, FP8, 4-bit formats, static batching, dynamic batching, and continuous batching change memory, kernels, quality, and latency.

July 1, 2026 11 min · read

1/21 - Inside the GPU: From SMs to HBM Without the Hand-Waving

A systems-level guide to GPU execution, SMs, warps, VRAM capacity, CUDA's memory hierarchy, occupancy, and the data movement that governs AI performance.

June 30, 2026 10 min · read

20/20 - Expert Parallelism: Routing Tokens Through a City of Specialists

How MoE routers, top-k expert selection, all-to-all communication, capacity, grouped GEMM, and load balancing shape expert-parallel inference.

June 28, 2026 10 min · read

19/20 - Prefill-Decode Disaggregation: Two Worker Pools, One Token Stream

A deep guide to separating prefill and decode workers, KV transfer, independent scaling, routing, RDMA, conditional disaggregation, and SLOs.

June 27, 2026 10 min · read

18/20 - Chunked Prefill: How to Stop One Long Prompt from Freezing Everyone Else

How chunked prefill divides long prompts, co-schedules them with decode, controls TTFT and TPOT interference, and chooses token budgets.

June 26, 2026 10 min · read

17/20 - Continuous Batching: The GPU Schedule That Never Stands Still

How iteration-level scheduling adds and removes LLM requests between decode steps, improving utilization while preserving fairness and latency.