---
cited_by:
  - '[[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: '2026-09-10'
number: 54713
source:
  - https://github.com/vllm-project/vllm/blob/b28c3e1568bfae930f61d4b24940e47528c85d4a/vllm/v1/core/kv_cache_coordinator.py
  - https://github.com/vllm-project/vllm/blob/b28c3e1568bfae930f61d4b24940e47528c85d4a/vllm/v1/core/single_type_kv_cache_manager.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#54713 [BugFix] Retain both replay boundaries so an EAGLE resend of a block-aligned prompt still hits'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/54713
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/54713
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/54713.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
aligned = request.num_prompt_tokens // scheduler_block_size \* scheduler_block_size · full dump: [[thoughts/inference/vllm-prs/54713|#54713]]

