---
cited_by:
  - '[[thoughts/papers/xie2026mhcmanifoldconstrainedhyperconnections#16-mhc-manifold-constrained-hyper-connections-with-v41s-delayedsingle-pass-pre|dsv41 §1.6]]'
  - '[[thoughts/inference/deepseek-v4.1-serving#4-pr-reading-order|dsv41 §4]]'
date: '2026-11-11'
kind: pr
local: []
merged: '2026-09-21'
number: 57603
source:
  - https://github.com/vllm-project/vllm/blob/9b49f92344312c41ad61e05282c8e6a2d9bafb7f/vllm/models/deepseek_v41/nvidia/ops/mhc.py
  - https://github.com/vllm-project/vllm/blob/9b49f92344312c41ad61e05282c8e6a2d9bafb7f/vllm/models/deepseek_v41/nvidia/model.py
  - https://github.com/vllm-project/vllm/blob/9b49f92344312c41ad61e05282c8e6a2d9bafb7f/vllm/model_executor/kernels/mhc/tilelang_kernels.py
  - https://github.com/vllm-project/vllm/blob/9b49f92344312c41ad61e05282c8e6a2d9bafb7f/vllm/models/deepseek_v41/nvidia/ops/mega_mhc.py
  - https://github.com/vllm-project/vllm/blob/9b49f92344312c41ad61e05282c8e6a2d9bafb7f/vllm/model_executor/kernels/mhc/warmup.py
state: merged
tags:
  - vllm
  - vllm-pr
  - new-architectures
title: '#57603 [Perf][DSV4.1] Overlap mHC coefficients for small TP batches'
topic: new-architectures
url: https://github.com/vllm-project/vllm/pull/57603
created: '2026-11-11'
modified: '2026-11-11'
published: '2026-11-11'
pageLayout: default
slug: hinterland/papers/maps/prs/57603
permalink: https://aarnphm.xyz/hinterland/papers/maps/prs/57603.md
generator:
  quartz: v4.6.0
  hostedProvider: Cloudflare
  baseUrl: aarnphm.xyz
full: https://aarnphm.xyz/llms-full.txt
---
Overlap shifted mHC coefficient generation with attention/FFN on small batches. The decoder keeps one post/pre path: the existing mHC dispatcher · full dump: [[thoughts/inference/vllm-prs/57603|#57603]]

