---
cited_by:
  - '[[thoughts/inference/kv-transfer#5-reading-order|reading-map §5]]'
date: '2026-11-11'
kind: pr
local:
  - file:///Users/aarnphm/workspace/vllm/vllm/v1/worker/kv_connector_model_runner_mixin.py
  - file:///Users/aarnphm/workspace/vllm/vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py
  - file:///Users/aarnphm/workspace/vllm/vllm/v1/worker/gpu_model_runner.py
  - file:///Users/aarnphm/workspace/vllm/vllm/distributed/kv_transfer/kv_connector/v1/base.py
  - file:///Users/aarnphm/workspace/vllm/vllm/v1/attention/backends/flash_attn.py
  - file:///Users/aarnphm/workspace/vllm/vllm/v1/attention/backends/flashinfer.py
merged: '2025-11-20'
number: 27743
source:
  - https://github.com/vllm-project/vllm/blob/647464719b131963dccdc3a28cfe52d1af293cda/vllm/v1/worker/kv_connector_model_runner_mixin.py
  - https://github.com/vllm-project/vllm/blob/647464719b131963dccdc3a28cfe52d1af293cda/vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py
  - https://github.com/vllm-project/vllm/blob/647464719b131963dccdc3a28cfe52d1af293cda/vllm/v1/worker/gpu_model_runner.py
  - https://github.com/vllm-project/vllm/blob/647464719b131963dccdc3a28cfe52d1af293cda/vllm/distributed/kv_transfer/kv_connector/v1/base.py
  - https://github.com/vllm-project/vllm/blob/647464719b131963dccdc3a28cfe52d1af293cda/vllm/attention/backends/abstract.py
  - https://github.com/vllm-project/vllm/blob/647464719b131963dccdc3a28cfe52d1af293cda/vllm/v1/kv_offload/cpu.py
  - https://github.com/vllm-project/vllm/blob/647464719b131963dccdc3a28cfe52d1af293cda/vllm/v1/attention/backends/flash_attn.py
  - https://github.com/vllm-project/vllm/blob/647464719b131963dccdc3a28cfe52d1af293cda/vllm/v1/attention/backends/flashinfer.py
state: merged
tags:
  - vllm
  - vllm-pr
  - hetero-tp-kv-layout
title: '#27743 [KVConnector][Core] Support cross-layer KV blocks'
topic: hetero-tp-kv-layout
url: https://github.com/vllm-project/vllm/pull/27743
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/27743
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/27743.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
Core of RFC [#27742](https://github.com/aarnphm/aarnphm.github.io/issues/27742). · full dump: [[thoughts/inference/vllm-prs/27743|#27743]]

