---
cited_by:
  - '[[thoughts/papers/kimiteam2026kimik3openfrontier#18-quant-formats|kimik3 §1.8]]'
date: '2026-11-11'
kind: pr
local: []
merged: '2026-09-18'
number: 57430
source:
  - https://github.com/vllm-project/vllm/blob/76d517fd1279805fa2318c28343fcd57b030ead3/vllm/models/kimi_k3/nvidia/model.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#57430 [Quantization] Support kimi-k3 routed expert quant'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/57430
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/57430
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/57430.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
## Background ## · full dump: [[thoughts/inference/vllm-prs/57430|#57430]]

