---
cited_by:
  - '[[thoughts/inference/replayssm-serving#5-pr-reading-order|replayssm §5]]'
date: '2026-11-11'
kind: pr
local:
  - file:///Users/aarnphm/workspace/vllm/vllm/v1/attention/backends/mamba_attn.py
  - file:///Users/aarnphm/workspace/vllm/vllm/model_executor/layers/mamba/mamba_mixer2.py
  - file:///Users/aarnphm/workspace/vllm/vllm/model_executor/layers/mamba/mamba_mixer.py
  - file:///Users/aarnphm/workspace/vllm/vllm/v1/worker/mamba_utils.py
  - file:///Users/aarnphm/workspace/vllm/vllm/platforms/interface.py
  - file:///Users/aarnphm/workspace/vllm/vllm/v1/worker/gpu_model_runner.py
  - file:///Users/aarnphm/workspace/vllm/vllm/v1/attention/backends/mamba1_attn.py
  - file:///Users/aarnphm/workspace/vllm/vllm/config/cache.py
merged: '2026-10-01'
number: 58997
source:
  - https://github.com/vllm-project/vllm/blob/cb6458c5ce61632524c0447d49790725c1e1d9a2/vllm/v1/attention/backends/mamba_attn.py
  - https://github.com/vllm-project/vllm/blob/cb6458c5ce61632524c0447d49790725c1e1d9a2/vllm/model_executor/layers/mamba/mamba_mixer2.py
  - https://github.com/vllm-project/vllm/blob/cb6458c5ce61632524c0447d49790725c1e1d9a2/vllm/model_executor/layers/mamba/mamba_mixer.py
  - https://github.com/vllm-project/vllm/blob/cb6458c5ce61632524c0447d49790725c1e1d9a2/vllm/v1/worker/mamba_utils.py
  - https://github.com/vllm-project/vllm/blob/cb6458c5ce61632524c0447d49790725c1e1d9a2/vllm/platforms/interface.py
  - https://github.com/vllm-project/vllm/blob/cb6458c5ce61632524c0447d49790725c1e1d9a2/vllm/v1/worker/gpu_model_runner.py
  - https://github.com/vllm-project/vllm/blob/cb6458c5ce61632524c0447d49790725c1e1d9a2/vllm/v1/attention/backends/mamba1_attn.py
  - https://github.com/vllm-project/vllm/blob/cb6458c5ce61632524c0447d49790725c1e1d9a2/vllm/config/cache.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#58997 [Core] Remove deprecated mamba_cache_mode "all"'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/58997
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/58997
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/58997.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
Remove `mamba_cache_mode="all"`, deprecated in [#55041](https://github.com/aarnphm/aarnphm.github.io/issues/55041) (v0.30.0). It is unsupported in MRV2 and never auto-selected (prefix caching defaults to `"align"`). `--mamba-cache-mode all` now fails validation. · full dump: [[thoughts/inference/vllm-prs/58997|#58997]]

