vllm-project/vllm-ascend

[Contribution] 任务 #13：长序列场景下pcp-dcp功能支持

Open

#10,660 opened on Jun 18, 2026

View on GitHub
 (3 comments) (0 reactions) (0 assignees)C++ (1,318 forks)github user discovery
help wanted

Repository metrics

Stars
 (2,180 stars)
PR merge metrics
 (Avg merge 4d 5h) (559 merged PRs in 30d)

Description

在提交新问题之前，请确保您已经在社区中搜索过相关问题，并使用了社区中提供的资源/工具后，仍未找到满意的解决方式。

📚 任务问题描述

任务描述

该任务拆分自 #9079，任务 ID：#13。

vllm-ascend已在GQA和MLA模型上支持pcp和dcp，当前代码路径在 https://github.com/vllm-project/vllm-ascend/blob/main/vllm_ascend/worker/pcp_utils.py 。当前代码逻辑实现不清晰，且耦合较为严重，需要重构。

验收标准

  1. pcp_utils.py 可以快速适配新的attention后端。
  2. 各attention后端之间相互解耦。

对接人

@jyoung6652

认领状态

待认领

建议的替代/修复方案

请根据任务描述提交实现、测试或文档 PR，并在 PR 中关联本 issue 与 #9079；如实现过程中发现任务边界、使用指导或现有行为存在不合理之处，请同步补充说明和最小复现。

欢迎加入社区，感谢您对社区的贡献 🎉!

Contributor guide

Research direction
Study the current pcp utils.py implementation, identify the coupling points between attention backends, and design a modular structure that allows easy addition of new backends.
Tech stack
python
Domain
backend
Issue type
Refactor
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70