---
cited_by:
  - '[[thoughts/inference/architectures#5-four-things-called-replay|README §5]]'
  - '[[thoughts/inference/replayssm#4-which-models-use-it|replayssm §4]]'
date: '2026-11-11'
kind: pr
local:
  - file:///Users/aarnphm/workspace/vllm/vllm/v1/core/kv_cache_coordinator.py
  - file:///Users/aarnphm/workspace/vllm/vllm/v1/core/single_type_kv_cache_manager.py
merged: '2026-10-11'
number: 61012
source:
  - https://github.com/vllm-project/vllm/blob/2339bd39d661965b821bfbe652db8f536e0b3dcd/vllm/v1/core/kv_cache_coordinator.py
  - https://github.com/vllm-project/vllm/blob/2339bd39d661965b821bfbe652db8f536e0b3dcd/vllm/distributed/kv_transfer/kv_connector/v1/mooncake/store/coordinator.py
  - https://github.com/vllm-project/vllm/blob/2339bd39d661965b821bfbe652db8f536e0b3dcd/vllm/v1/core/single_type_kv_cache_manager.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#61012 [Bugfix][Mooncake] Use the EAGLE replay boundary when retaining sliding-window tails'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/61012
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/61012
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/61012.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
`MooncakeStoreCoordinator.store_mask` mirrors the core’s sparse sliding-window retention (`SlidingWindowManager.reachable_block_mask`) so the store keeps the same tails the local prefix cache does. It passed the non-EAGLE replay boundary… · full dump: [[thoughts/inference/vllm-prs/61012|#61012]]

