---
cited_by:
  - '[[thoughts/inference/kimi-k3-state#34-pd-dcp-kv-offload-59229-test-matrix|kimik3 §3.4]]'
date: '2026-11-11'
kind: pr
local:
  - file:///Users/aarnphm/workspace/vllm/vllm/v1/attention/backends/mla/flashinfer_mla.py
merged: '2026-10-27'
number: 59392
source:
  - https://github.com/vllm-project/vllm/blob/8697bbae4c7d4c15591bb85784835eeab2c8ecb1/vllm/v1/attention/backends/mla/flashinfer_mla.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#59392 [Bugfix][Attention] Fix FlashInfer MLA DCP decode on ragged spec-decode batches'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/59392
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/59392
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/59392.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
ValueError: causal_seqlens_kv_global must have shape (9,), got (2,) · full dump: [[thoughts/inference/vllm-prs/59392|#59392]]

