---
cited_by:
  - '[[thoughts/inference/deepseek-v4.1-serving#4-pr-reading-order|dsv41 §4]]'
date: '2026-11-11'
kind: pr
local:
  - file:///Users/aarnphm/workspace/vllm/.github/mergify.yml
  - file:///Users/aarnphm/workspace/vllm/vllm/model_executor/models/registry.py
merged: '2026-09-14'
number: 56741
source:
  - https://github.com/vllm-project/vllm/blob/cf1584f373d06f03c5662608fb80cf66c03fcb1d/vllm/models/deepseek_v41/attention.py
  - https://github.com/vllm-project/vllm/blob/cf1584f373d06f03c5662608fb80cf66c03fcb1d/vllm/models/deepseek_v41/amd/rocm.py
  - https://github.com/vllm-project/vllm/blob/cf1584f373d06f03c5662608fb80cf66c03fcb1d/vllm/models/deepseek_v41/nvidia/engram.py
  - https://github.com/vllm-project/vllm/blob/cf1584f373d06f03c5662608fb80cf66c03fcb1d/vllm/models/deepseek_v41/nvidia/flashinfer_sparse.py
  - https://github.com/vllm-project/vllm/blob/cf1584f373d06f03c5662608fb80cf66c03fcb1d/vllm/models/deepseek_v41/nvidia/flashmla.py
  - https://github.com/vllm-project/vllm/blob/cf1584f373d06f03c5662608fb80cf66c03fcb1d/vllm/models/deepseek_v41/nvidia/model.py
  - https://github.com/vllm-project/vllm/blob/cf1584f373d06f03c5662608fb80cf66c03fcb1d/.github/mergify.yml
  - https://github.com/vllm-project/vllm/blob/cf1584f373d06f03c5662608fb80cf66c03fcb1d/vllm/model_executor/models/registry.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#56741 [Refactor] Normalize DeepSeek V4.1 model package naming'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/56741
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/56741
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/56741.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
Rename `vllm/models/deepseek_v4_1/` to `vllm/models/deepseek_v41/`, following the existing `deepseek_v32` convention and the V4.1 config/frontend naming. Update Python imports, lazy model and attention registration strings, test… · full dump: [[thoughts/inference/vllm-prs/56741|#56741]]

