---
cited_by:
  - '[[thoughts/inference/dflash2|reading-map §2.2]]'
date: '2026-11-11'
kind: pr
local: []
merged: '2026-10-08'
number: 56983
source:
  - https://github.com/vllm-project/vllm/blob/2274e86842d6e59a5f9f9d1fb6cc1dd2d2bf8350/vllm/models/glm5next/common/model.py
state: merged
tags:
  - vllm
  - vllm-pr
  - specdec
title: '#56983 [Spec Decode][Model] Support DFlash2 draft models with GLM-5.3-Flash'
topic: specdec
url: https://github.com/vllm-project/vllm/pull/56983
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/56983
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/56983.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
\[Model\] Support DFlash2 draft models with GLM-5.3-Flash · full dump: [[thoughts/inference/vllm-prs/56983|#56983]]

