---
cited_by:
  - '[[thoughts/inference/kimi-k3-state#34-pd-dcp-kv-offload-59229-test-matrix|kimik3 §3.4]]'
  - '[[thoughts/inference/kimi-k3-prs#4-pr-reading-order|kimik3 §4]]'
date: '2026-11-11'
kind: pr
local:
  - file:///Users/aarnphm/workspace/vllm/.buildkite/test_areas/models_basic.yaml
merged: '2026-10-02'
number: 59229
source:
  - https://github.com/vllm-project/vllm/blob/d648847fe451a6a0366f8dd0e1ae96804a49a299/.buildkite/test_areas/models_basic.yaml
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#59229 [CI][Kimi-K3] Test prefix cache reuse with KV offload, P/D and DCP'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/59229
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/59229
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/59229.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
Kimi-K3 has no end-to-end prefix-cache coverage. FlashKDA exports Mamba prefill checkpoints, a path the Qwen3.5-based `test_hybrid_prefix_cache_hit_rate.py` never takes, so regressions such as the dropped prompt-end checkpoint fixed by… · full dump: [[thoughts/inference/vllm-prs/59229|#59229]]

