Week 85 — vLLM internals

LLM inference and performance engineering · Read / diagram

Hard

Phase 8 — LLM inference and performance engineering

Overview

Scheduler, block manager, code paths

Mode this week: read_diagram. Match the work to that mode (operating model): implement ships running code; read/diagram ships a doc; deploy/benchmark ships a measured run. Personal dates, checkboxes, and the RPG layer stay in a learner journal.

Core deliverable

Internal anatomy notes

Optional depth

Add a production-shaped benchmark, cost or safety analysis, and an architecture trade-off note.

Week loop (from the cookiecutter journal)

Mon — Theory: Scheduler, block manager, code paths
Tue — Build: start the core deliverable above
Wed — Systems / papers: one paper or system note (see below if this week has assigned reading)
Thu — Eval / interview: write the four evidence items
Fri — Algorithmic Forge: Scheduler benchmark; Week 93 inference boss (45-120 min; Core / Supporting)

Forge theme: Priority scheduling, interval allocation, capacity search, randomized load balancing

Leetcode Darbar (parallel)

This week's band (82-102): Heaps, priority queues, graphs, trees, range queries. Production connection: Inference schedulers, quotas, queues, tenant fairness.

Standard: one aligned problem. Auror: the five-slot queue on the Darbar page. Tracker stays in the learner journal.

Topics: graphs · heap · queue · range query · trees

All Paths From Source To Target · medium · graphs
The K Weakest Rows In A Matrix · easy · heap
Implement Stack Using Queues · easy · queue
Queue Reconstruction By Height · medium · range query
Binary Tree Paths · easy · trees

Evidence contract

Every core week records all four (cookiecutter journal/weeks/week_085.md):

Code / implementation (or the design artifact on a writing week)
Benchmark / result
Design doc / technical explanation
Retrospective / learning note (Sailboat: destination, wind, anchor, rocks, heading)

On this site

Official Tensor-to-Tenant

Week 85 of Tensor-to-Tenant · Previous week · Next week.