---
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: '2026-09-28'
number: 58961
source:
  - https://github.com/vllm-project/vllm/blob/a2be4d3cc7b978a6720dab32d28ae310775acb16/vllm/models/qwen4_exp/common/qsa_cache.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#58961 [Bugfix][Qwen4Exp] Release the profiling KV cache held by QSA key views'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/58961
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/58961
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/58961.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
Fixes [#58960](https://github.com/aarnphm/aarnphm.github.io/issues/58960). · full dump: [[thoughts/inference/vllm-prs/58961|#58961]]

