---
cited_by:
  - '[[thoughts/inference/replayssm-serving#5-pr-reading-order|replayssm §5]]'
date: '2026-11-11'
kind: pr
local: []
merged: '2026-08-03'
number: 50424
source:
  - https://github.com/vllm-project/vllm/blob/b977407d8be3bc076c1e2d6f3df02b9bdbd1fab9/vllm/model_executor/models/qwen3_dspark.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#50424 Support quantized DSpark Markov heads'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/50424
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/50424
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/50424.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
Add quantization configuration support to the DSpark Markov head. · full dump: [[thoughts/inference/vllm-prs/50424|#50424]]

