Add fused_partial_rope op

[lshpku]

PR Category

Operator Mechanism

PR Types

New features

Description

新增paddle.incubate.nn.functional.fused_partial_rope(x, cos, sin)算子

该算子是DeepseekV3使用的一种“部分RoPE“算子，即对于输入 x[bs, seq_len, num_heads, head_dim]，首先将 head_dim 拆分成 nope_head_dim + pe_head_dim，然后只在 pe_head_dim 上进行RoPE，最后合并回来

注意到，该算子只有一个输入x，因此 q 和 k 需要分别处理；这是模仿DSV3的timeline实现的，因为它的 q 比 k 大很多，分开处理更好实现

PaddleNLP修改已合入：PaddlePaddle/PaddleNLP#10942
（用了分支的形式，旧版的Paddle还能跑老的分支，新版Paddle就自动使用融合算子）

Pcard-85711

[paddle-bot]

你的PR提交成功，感谢你对开源项目的贡献!
请关注后续CI自动化测试结果，详情请参考Paddle-CI手册。
Your PR has been submitted. Thanks for your contribution!
Please wait for the result of CI firstly. See Paddle CI Manual for details.

[codecov-commenter]

Codecov Report

❌ Patch coverage is 97.29730% with 1 line in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@b5cf3c5). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
...addle/incubate/nn/functional/fused_partial_rope.py	88.88%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             develop   #74577   +/-   ##
==========================================
  Coverage           ?   97.29%           
==========================================
  Files              ?        3           
  Lines              ?       37           
  Branches           ?        0           
==========================================
  Hits               ?       36           
  Misses             ?        1           
  Partials           ?        0           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.