Add AMD tasks for Hackathon 10th#1232
Open
M4jupitercannon wants to merge 3 commits intoPaddlePaddle:masterfrom
Open
Add AMD tasks for Hackathon 10th#1232M4jupitercannon wants to merge 3 commits intoPaddlePaddle:masterfrom
M4jupitercannon wants to merge 3 commits intoPaddlePaddle:masterfrom
Conversation
- Add check-in task: PaddleOCR-VL-1.5 deployment on AMD GPU (pfcc/paddle-hardware/) - Add advanced task: HIP BF16 precision type adaptation for Paddle framework (hackathon/hackathon_10th/) Made-with: Cursor
luotao1
reviewed
Mar 13, 2026
| 1. 向 [Paddle 主仓库](https://github.com/PaddlePaddle/Paddle) develop 分支提交 Issue 描述问题，并提交 PR 实现 HIP BF16 精度类型适配 | ||
| 2. 向 [PaddleX 仓库](https://github.com/PaddlePaddle/PaddleX) develop 分支提交 Issue 和 PR，移除现有 ROCm BF16 的 workaround 代码 | ||
| 3. PR 中需包含测试用例和在 AMD GPU 上的验证结果截图 | ||
| * 提交方式：GitHub Issue + PR 并截图发送邮件 |
| * [PaddleX ROCm BF16 现有 workaround](https://github.com/PaddlePaddle/PaddleX/compare/release/3.3...vivienfanghuagood:PaddleX:dev_rocm70) | ||
| * [PaddleOCR-VL-1.5 模型](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.5) | ||
| * [MIOpen 文档](https://rocm.docs.amd.com/projects/MIOpen/en/latest/) | ||
| * PaddleOCR-VL AMD GPU 部署教程：参见本期打卡任务指导 |
Collaborator
There was a problem hiding this comment.
PaddleOCR-VL AMD GPU 部署教程：参见本期打卡任务指导。可附上链接
| * 【GitHub ID】：XXX | ||
| * 【打卡内容】：PaddleOCR-VL-1.5 推理 | ||
| * 【打卡截图】： | ||
| * vLLM 后端或 Native 后端推理结果截图（任选其一） |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
pfcc/paddle-hardware/PaddleOCR-VL-AMD-GPU打卡任务.md)hackathon/hackathon_10th/【Hackathon_10th】硬件生态任务合集.mdunder AMD section)Details
打卡任务
PaddleOCR-VL-1.5 在 AMD GPU 上的部署与运行，包含：
进阶任务
为 Paddle 框架适配 HIP BF16 精度类型，使 PaddleOCR-VL 等模型在 ROCm 上可原生使用 BF16 精度推理。