Tagged “#llm-inference”

• A Token's Journey Across the LLM Stack

  Part 4 of The Life of a Token Across the LLM Stack: a synthesis of token, compute, memory, and request lifecycles for diagnosing LLM inference systems.

  06 Jun 2026 · 17 min read · Wenbo Ji

• The Life of a Request Inside vLLM

  Part 3 of The Life of a Token Across the LLM Stack: a serving-level walkthrough of how vLLM-style engines schedule prefill, decode, continuous batching, KV cache, and streamed tokens.

  04 Jun 2026 · 18 min read · Wenbo Ji

• Why Transformer Performance Is Mostly a Matmul Problem

  Part 2 of The Life of a Token Across the LLM Stack: a kernel-level explanation of how Transformer linear layers become GPU matmul, tiling, memory movement, and tensor-core execution.

  02 Jun 2026 · 17 min read · Wenbo Ji

• The Life of a Token Inside a Transformer

  Part 1 of The Life of a Token Across the LLM Stack: a systems-oriented explanation of how tokens move through embeddings, attention, MLPs, positional encoding, KV cache, and logits.

  31 May 2026 · 17 min read · Wenbo Ji

• LLM Inference Is a Full-Stack Systems Problem

  Part 0 of The Life of a Token Across the LLM Stack: an entry-point map of LLM inference across Transformer computation, GPU kernels, KV cache, and serving systems.

  29 May 2026 · 16 min read · Wenbo Ji

See all tags.