---
cited_by:
  - '[[thoughts/inference/architectures#6-reading-order|README §6]]'
  - '[[thoughts/inference/deepseek-v4.1-serving#4-pr-reading-order|dsv41 §4]]'
date: '2026-11-11'
kind: pr
local: []
merged: '2026-09-10'
number: 56228
source:
  - https://github.com/vllm-project/vllm/blob/9b959b86577c082c0b2bf9e2c22263255a36ad83/vllm/models/deepseek_v4_1/common/ops/cache_utils.py
  - https://github.com/vllm-project/vllm/blob/9b959b86577c082c0b2bf9e2c22263255a36ad83/vllm/models/deepseek_v4_1/attention.py
  - https://github.com/vllm-project/vllm/blob/9b959b86577c082c0b2bf9e2c22263255a36ad83/vllm/models/deepseek_v4_1/nvidia/model.py
  - https://github.com/vllm-project/vllm/blob/9b959b86577c082c0b2bf9e2c22263255a36ad83/vllm/models/deepseek_v4_1/amd/model.py
  - https://github.com/vllm-project/vllm/blob/9b959b86577c082c0b2bf9e2c22263255a36ad83/vllm/models/deepseek_v4_1/common/engram.py
  - https://github.com/vllm-project/vllm/blob/9b959b86577c082c0b2bf9e2c22263255a36ad83/vllm/models/deepseek_v4_1/nvidia/flashinfer_sparse.py
  - https://github.com/vllm-project/vllm/blob/9b959b86577c082c0b2bf9e2c22263255a36ad83/vllm/models/deepseek_v4_1/amd/rocm.py
  - https://github.com/vllm-project/vllm/blob/9b959b86577c082c0b2bf9e2c22263255a36ad83/vllm/models/deepseek_v4_1/nvidia/dspark.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#56228 [Model] DeepSeek-V4.1-Flash Model Definitions'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/56228
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/56228
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/56228.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
Adds the new `vllm/models/deepseek_v4_1/` model definition package (nvidia, amd, and common code paths) · full dump: [[thoughts/inference/vllm-prs/56228|#56228]]

