Beginner score
48/100
Competition workspace
适合已有大模型推理工程经验、能在资源受限的端侧环境做性能优化的高校学生、个人开发者或企业开发者。尤其适合熟悉量化、推理内核、异构计算，或希望针对 RISC-V 构建推理框架、算子库和编译器的团队；多人参赛时需能组成 2—3 人队伍。
Suggested next step
Decide whether this contest fits your current stage before you sink time into the leaderboard.
Beginner score
48/100
Learning value
60/100
Estimated effort
12-40 hours
Metric
Official scoring is published on the Op…
适合已有大模型推理工程经验、能在资源受限的端侧环境做性能优化的高校学生、个人开发者或企业开发者。尤其适合熟悉量化、推理内核、异构计算，或希望针对 RISC-V 构建推理框架、算子库和编译器的团队；多人参赛时需能组成 2—3 人队伍。
If the items below still feel unfamiliar, you usually get a better result by preparing first instead of rushing in.
大模型量化与剪枝
LLM 推理性能分析
CPU/GPU/NPU 异构调度
RISC-V 架构优化
Linux 部署与调试
Git 与开源许可证合规
The real friction is usually not library usage. It is validation, time allocation, and task framing.
难点不只是把模型跑起来，而是在 openKylin 端侧有限的 CPU/GPU/NPU 资源上，同时证明吞吐、延迟或实时性提升且尽量不损失精度，并兼顾不同硬件架构的适配。决赛还要求提交可运行代码和可现场演示的环境，代码、文档、验证结果及开源合规都需要做到可复现。
This guide is the best pre-read if you want a cleaner start instead of trial-and-error.
How to learn feature engineering, validation, and competition workflow without heavy hardware.
No GPU? Pick Competitions That Still Teach You Good HabitsUse these fields to make a quick decision before you dive deeper.
Registration is unverified; confirm availability on the official page before investing.
Sign in to save competitions and build your own shortlist.
Rules, files, submission details, and the live deadline still come from the official page.
These competitions share a similar domain or difficulty level.
Separate what is confirmed from what still needs review. Official rules and deadlines win — report anything that looks wrong.
Official metric is not published on the OpenAtom competition listing; verify scoring on the competition page.
reward_value_usd is a rough CNY→USD estimate (×0.14) for ranking only; use reward_summary for the official prize text.