Files
vllm-omni/docs/design/module/cache_management.md
T
2026-08-10 19:25:03 +08:00

1.2 KiB

title, kind, status, owners, primary_code_paths, related_code_paths, depends_on, validation_paths, upstream_refs, last_reviewed
title kind status owners primary_code_paths related_code_paths depends_on validation_paths upstream_refs last_reviewed
Cache Management module draft
@Isotr0py
@princepride
@SamitHuang
vllm_omni/diffusion/cache/**
vllm_omni/experimental/ar_diffusion/kv_cache/**
vllm_omni/core/**
ar_runtime.md
diffusion/diffusion_runtime.md
tests/diffusion/cache/**
vllm.v1.core.kv_cache_manager
2026-07-16

Cache management

Cache management defines reusable state, cache identity, validity, lifecycle, and eviction across AR and diffusion execution.

Candidate invariants

CACHE-INV-001: Cache identity is complete

Rule: A cache key MUST include every input and execution property that can change the reused value.

CACHE-INV-002: Reuse preserves correctness

Rule: A cache optimization MUST provide a disabled path and MUST NOT reuse state after its validity conditions change.

CACHE-INV-003: Ownership has an end

Rule: Request-scoped and model-scoped cache entries MUST have explicit reset, eviction, or teardown behavior.

Safe-change guide

Test hit, miss, invalidation, disabled, concurrent-request, and teardown paths.