---
cited_by:
  - '[[thoughts/inference/kimi-k3#5-sharp-edges-each-fix-shows-an-invariant|kimik3 §5]]'
date: '2026-11-11'
kind: pr
local:
  - file:///Users/aarnphm/workspace/vllm/vllm/model_executor/layers/attention/mla_attention.py
merged: '2026-09-11'
number: 56429
source:
  - https://github.com/vllm-project/vllm/blob/127143e27f2ba15e3b0ee6f4d73eaeaa60097bc2/vllm/model_executor/layers/attention/mla_attention.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#56429 Revert "[Rocm][Kimi-k3] Fix pipeline_parallel support for the kimik3 DCP mode  (#53664)"'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/56429
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/56429
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/56429.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
This PR reverts [#53664](https://github.com/aarnphm/aarnphm.github.io/issues/53664) (“\[Rocm\]\[Kimi-k3\] Fix pipeline_parallel support for the kimik3 DCP mode”). That PR added a fallback in `MLAAttentionLayer.build()` that derives `dcp_local_seq_lens` from `seq_lens` whenever `CommonAttentionMetadata`… · full dump: [[thoughts/inference/vllm-prs/56429|#56429]]

