[2025秋季][2-2-3] HX-1234 #166

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Open

HX-1234 wants to merge 1 commit into InfiniTensor:main from HX-1234:2025-autumn-HX-1234-2-2-3

+958 −0

HX-1234 commented Dec 26, 2025 •

edited

Loading

赛题信息

赛题号：2-2-3
题目名称：DeepSeek-V3 Multi-Head Latent Attention (MLA) 模块

测试结果截图

1. 正确性测试 (Correctness)

验证脚本：test/models/DeepSeek-R1/check_mla_correctness.py

2. 性能测试 (Benchmark)

测试脚本：test/models/DeepSeek-R1/test_mla_hf_golden.py
测试脚本：test/models/DeepSeek-R1/test_mla_torch_golden.py

附件

赛题报告 (包含在官网附件压缩包中和中期报告上传入口中)
HONOR_CODE.md


          [2-2-3] MLA implementation by HX-1234

7c1bd87

HX-1234 requested a review from a team

December 26, 2025 10:40

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet