---
cited_by:
  - '[[thoughts/inference/qwen3.8-serving#3-kv-cache--state-what-lives-where-per-request|qwen4next §3]]'
  - '[[thoughts/inference/qwen3.8-serving#4-pr-reading-order-vllm-main-git-show-sha|qwen4next §4]]'
  - '[[thoughts/inference/qwen3.8-serving#5-sharp-edges-bugs-that-expose-invariants|qwen4next §5]]'
date: '2026-11-11'
kind: pr
local: []
merged: '2026-09-25'
number: 58489
source:
  - https://github.com/vllm-project/vllm/blob/48d8880d098c567c64150203110b6a6a4221d44f/vllm/models/qwen4_exp/nvidia/ngram_embedding.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#58489 [Bugfix][Qwen4Exp] Keep pinned PLE prefetch ids out of the CUDA graph pool'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/58489
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/58489
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/58489.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
## Problem and fix · full dump: [[thoughts/inference/vllm-prs/58489|#58489]]

