---
cited_by:
  - '[[thoughts/inference/qwen3.8-serving#5-sharp-edges-bugs-that-expose-invariants|qwen4next §5]]'
date: '2026-11-11'
kind: pr
local: []
merged: '2026-09-02'
number: 54722
source:
  - https://github.com/vllm-project/vllm/blob/1e300895acecd29fa037616b59d793aae164c4ea/vllm/models/qwen4_exp/nvidia/ple_layer.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#54722 [Qwen4] validate FP8 PLE weight scale after loading'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/54722
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/54722
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/54722.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
Fix a fail-open risk in the Qwen3.8 Flash Next FP8 PLE weight loading path. · full dump: [[thoughts/inference/vllm-prs/54722|#54722]]

