Async and Hogwild! Inference

Speculative decoding (Phase 10 · 15) parallelizes tokens within one sequence. Multi-agent frameworks parallelize across whole sequences but force explicit coordination (voting, sub-task splitting). Hogwild! Inference (Rodionov et al., arXiv:2504.06261) does something else: run N instances of the same LLM in parallel against a SHARED key-value cache. Each worker sees every other worker's generated tokens instantly. Modern reasoning models — QwQ, DeepSeek-R1 — can self-coordinate through that shared cache without any fine-tuning. The approach is experimental but it opens an entirely new axis of inference parallelism that sits orthogonal to spec decode. This lesson implements a two-worker Hogwild! simulator in stdlib Python and explains why the shared-cache collaboration emerges from the existing model's reasoning abilities.

Build 1 hr Python (stdlib)

Prerequisites: Phase 10 · 12 (inference optimization), Phase 10 · 15 (speculative decoding)

#Learning Objectives

Describe the three common parallel-LLM topologies (voting, sub-task, Hogwild!) and name which problems each one targets.
State the core Hogwild! setup: multiple workers, one shared KV cache, emergent coordination via self-prompting.
Compute the wall-time speedup of Hogwild! as a function of worker count N, task-level parallelism p, and coordination overhead c.
Implement a two-worker Hogwild! simulator on a toy problem and observe the emergent task division.

#Learning Objectives

Keep going. The rest of this lesson is one step away.