vllm-project/vllm-ascend

[Contribution] 任务 #16：Gemma4 E2B/E4B轻量级图片、语音、文本多模态大模型适配

Open

#10,663 opened on Jun 18, 2026

View on GitHub
 (7 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：#16。

适配Gemma4轻量级多模态大模型，标准架构，但是存在Head-dim为512的情况，需验证KV Cache层间共享特性。

验收标准

  1. 在 tests/e2e/models/configs 添加完整测试用例。
  2. 在 docs/source/tutorials/models 创建模型适配教程文档。
  3. 在对应issue下提交 SKILL.md（记录AI辅助开发经验、有效提示词及最佳实践）。

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 Gemma4 architecture, particularly head dim 512 and KV cache sharing across layers. Implement test cases in tests/e2e/models/configs and create documentation in docs/source/tutorials/models. Also prepare SKILL.md with AI assisted development tips.
Tech stack
python
Domain
aimachine learningbackendinfrastructure
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
3-5 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
GitPythonC++
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40