---
cited_by:
  - '[[thoughts/inference/architectures#3-what-changed-in-vllms-kv-cache-manager-to-hold-these|README §3]]'
  - '[[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:
  - file:///Users/aarnphm/workspace/vllm/vllm/v1/attention/backends/mla/indexer.py
merged: '2026-10-08'
number: 59528
source:
  - https://github.com/vllm-project/vllm/blob/240785b82c299c6c08bc5239e997cf62d67cf7bb/vllm/v1/attention/backends/mla/indexer.py
  - https://github.com/vllm-project/vllm/blob/240785b82c299c6c08bc5239e997cf62d67cf7bb/vllm/models/qwen4_exp/common/qsa_cache.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#59528 [Bugfix] Keep the GLM-5.3 kpool tail and Qwen4 QSA ring out of the null block'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/59528
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/59528
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/59528.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
GLM-5.3-Flash kpool tail: `_kpool_tail_slot_mapping_kernel` maps every token to `block_table[req][0] * kpool + pos % kpool`. Its torch fallback does the same. · full dump: [[thoughts/inference/vllm-prs/59528|#59528]]

