---
cited_by:
  - '[[thoughts/inference/architectures#6-reading-order|README §6]]'
  - '[[thoughts/inference/qwen3.8-serving#4-pr-reading-order-vllm-main-git-show-sha|qwen4next §4]]'
date: '2026-11-11'
kind: pr
local: []
merged: '2026-08-31'
number: 53896
source:
  - https://github.com/vllm-project/vllm/blob/e126687a9a828d513c01a07cd69f025f27d63280/vllm/models/qwen4_exp/amd/ple_layer.py
  - https://github.com/vllm-project/vllm/blob/e126687a9a828d513c01a07cd69f025f27d63280/vllm/models/qwen4_exp/amd/ops/qsa.py
  - https://github.com/vllm-project/vllm/blob/e126687a9a828d513c01a07cd69f025f27d63280/vllm/models/qwen4_exp/amd/model.py
  - https://github.com/vllm-project/vllm/blob/e126687a9a828d513c01a07cd69f025f27d63280/vllm/models/qwen4_exp/nvidia/model.py
  - https://github.com/vllm-project/vllm/blob/e126687a9a828d513c01a07cd69f025f27d63280/vllm/models/qwen4_exp/common/qsa_cache.py
  - https://github.com/vllm-project/vllm/blob/e126687a9a828d513c01a07cd69f025f27d63280/vllm/models/qwen4_exp/amd/ops/hc.py
  - https://github.com/vllm-project/vllm/blob/e126687a9a828d513c01a07cd69f025f27d63280/vllm/models/qwen4_exp/amd/qsa.py
  - https://github.com/vllm-project/vllm/blob/e126687a9a828d513c01a07cd69f025f27d63280/vllm/models/qwen4_exp/amd/mtp.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#53896 [Model] Support Qwen3.8-Flash-Next'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/53896
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/53896
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/53896.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
Support Qwen3.8-Flash-Next · full dump: [[thoughts/inference/vllm-prs/53896|#53896]]

