support qkdim!=vdim

[chang-wenbin]

Motivation

💡 If this PR is a Cherry Pick, the PR title needs to follow the format by adding the [Cherry-Pick] label at the very beginning and appending the original PR ID at the end. For example, [Cherry-Pick][CI] Add check trigger and logic(#5191)

💡 如若此PR是Cherry Pick，PR标题需遵循格式，在最开始加上[Cherry-Pick]标签，以及最后面加上原PR ID，例如[Cherry-Pick][CI] Add check trigger and logic(#5191)

Modifications

Usage or Command

Accuracy Tests

Checklist

• Add at least a tag in the PR title.
  • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
  • You can add new tags based on the PR content, but the semantics must be clear.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
• Provide accuracy results.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

[codecov-commenter]

Codecov Report

❌ Patch coverage is 52.77778% with 17 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@edc885d). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
fastdeploy/model_executor/layers/linear.py	57.69%	10 Missing and 1 partial ⚠️
...l_executor/layers/attention/append_attn_backend.py	50.00%	2 Missing and 2 partials ⚠️
...astdeploy/model_executor/ops/triton_ops/do_rope.py	0.00%	2 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #8023   +/-   ##
==========================================
  Coverage           ?   67.67%           
==========================================
  Files              ?      471           
  Lines              ?    66360           
  Branches           ?    10217           
==========================================
  Hits               ?    44912           
  Misses             ?    18576           
  Partials           ?     2872           

Flag	Coverage Δ
GPU	77.73% <52.77%> (?)
XPU	6.99% <0.00%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Harness.
📢 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.

[PaddlePaddle-bot]

🤖 Paddle-CI-Agent | ci_status_monitor | 2026-06-17 22:03:35

CI报告基于以下代码生成（30分钟更新一次）:
PR commit: 94fa1f9 | Merge base: edc885d (branch: develop)

---

1 Required任务 : 8/10 通过

总执行（rerun次数）	总任务	✅ 通过	❌ 失败	⏳ 运行中	⏸️ 等待中	跳过
42(0)	42	37	5	0	0	0

任务	错误类型	置信度	日志
Run FastDeploy Unit Tests and Coverage / run_tests_with_coverage	未知	低	Job
Extracted partial CE model tasks to run in CI. / run_ce_cases	未知	低	Job

2 失败详情

🔴 Run FastDeploy Unit Tests and Coverage / run_tests_with_coverage — 未知（置信度: 低）

错误类型: 未知 | 置信度: 低
分析器: 通用分析(fallback)
失败用例: 分析不可用

用例	错误摘要
未提取到具体失败用例	深度日志未返回 log_file_path、unittest_details 或 step_log；仅有 Process completed with exit code 8.

关键日志:

[FAILURE]: Process completed with exit code 8.
深度日志返回：日志获取失败，无法提取错误信息

• 根因摘要: 分析不可用，缺少可定位日志
  深度日志接口没有返回可读取的单测日志或 traceback，无法确认是否由本 PR 的 qkdim/vdim 相关改动触发。PR 变更涉及 append_attn_backend.py、linear.py、do_rope.py 和 tests/model_executor/test_linear.py，但当前日志不足以建立直接因果关系。

修复建议:

1. 先 rerun 或重新拉取该 job 日志；拿到具体失败用例/traceback 后再定位源码。
2. 若重现，请重点检查 PR 修改的 q/k/v cache shape、qk_rmsnorm_fused/do_rope 调用参数和 QKV/Gate 权重分片 offset。

关联变更: fastdeploy/model_executor/layers/attention/append_attn_backend.py, fastdeploy/model_executor/layers/linear.py, fastdeploy/model_executor/ops/triton_ops/do_rope.py, tests/model_executor/test_linear.py

🔴 Extracted partial CE model tasks to run in CI. / run_ce_cases — 未知（置信度: 低）

错误类型: 未知 | 置信度: 低
分析器: 通用分析(fallback)
失败用例: 分析不可用

用例	错误摘要
未提取到具体失败用例	深度日志未返回 log_file_path、unittest_details 或 step_log；仅有 Process completed with exit code 123.

关键日志:

[FAILURE]: Process completed with exit code 123.
深度日志返回：日志获取失败，无法提取错误信息

• 根因摘要: 分析不可用，缺少 CE 失败详情
  深度日志接口没有返回 CE case 的具体命令、失败模型或 traceback；因此无法判断失败是否与本 PR 的 q/k/v 维度支持改动直接相关。当前只能确认该 required job 在 PR Build and Test workflow 中失败。

修复建议:

1. 先 rerun 或补充该 job 的完整日志；拿到失败模型和错误堆栈后再定位。
2. 若 CE case 与新增 v_head_dim 场景相关，请优先核对 QKV 输出维度、KV cache value shape 和权重加载分片 offset 是否一致。

关联变更: fastdeploy/model_executor/layers/attention/append_attn_backend.py, fastdeploy/model_executor/layers/linear.py, fastdeploy/model_executor/ops/triton_ops/do_rope.py

[PaddlePaddle-bot]

🤖 Paddle-CI-Agent | pr_review | 2026-06-11 02:07:41 Asia/Shanghai

📋 Review 摘要

PR 概述：为 attention/QKV 路径补充 qkdim != vdim 支持。
变更范围：AppendAttention backend、QKV/QKVG linear loader、Triton RoPE、线性层单测。
影响面 Tag：[OP] [KVCache] [Loader]

问题

级别	文件	概述
🔴 Bug	fastdeploy/model_executor/layers/attention/append_attn_backend.py:324	v_head_dim != head_dim 会无条件执行 q/k RMSNorm，未启用 qk norm 的模型会把 None 传进 Triton kernel
🟡 建议	tests/model_executor/test_linear.py:291	新增测试仍使用 v_head_dim == head_dim，没有覆盖本 PR 的核心维度不等分支

📝 PR 规范检查

标题缺少官方 Tag，且 PR 描述的 Motivation / Modifications / Usage or Command / Accuracy Tests 仍未填写。

标题建议（可直接复制）：

• [OP] Support qkdim != vdim in attention and QKV loading

PR 描述建议（点击展开，可直接复制）

## Motivation
Support models whose Q/K head dimension differs from V head dimension (`qkdim != vdim`) in FastDeploy attention and QKV projection paths.

## Modifications
- Add `v_head_dim` to attention backend constructors and use it for value cache shape.
- Pass `model_config.v_head_dim` from GPU model runner to the selected attention backend.
- Update QKV/QKVG parallel linear output sizing and V shard placement to use `v_head_dim`.

## Usage or Command
N/A

## Accuracy Tests
N/A. Current PR does not include accuracy or regression test results.

## Checklist

- [x] Add at least a tag in the PR title.
  - Tag list: [`[FDConfig]`,`[APIServer]`,`[Engine]`, `[Scheduler]`, `[PD Disaggregation]`, `[Executor]`, `[Graph Optimization]`, `[Speculative Decoding]`, `[RL]`, `[Models]`, `[Quantization]`, `[Loader]`, `[OP]`, `[KVCache]`, `[DataProcessor]`, `[BugFix]`, `[Docs]`, `[CI]`, `[Optimization]`, `[Feature]`, `[Benchmark]`, `[Others]`, `[XPU]`, `[HPU]`, `[GCU]`, `[DCU]`, `[Iluvatar]`, `[Metax]`]
  - You can add new tags based on the PR content, but the semantics must be clear.
- [ ] Format your code, run `pre-commit` before commit.
- [ ] Add unit tests. Please write the reason in this PR if no unit tests.
- [ ] Provide accuracy results.
- [x] If the current PR is submitting to the `release` branch, make sure the PR has been submitted to the `develop` branch, then cherry-pick it to the `release` branch with the `[Cherry-Pick]` PR tag.

[PaddlePaddle-bot]

这里把 external_norm_rope 只和 v_head_dim != head_dim 绑定后，会对所有 qk/v 维度不同的层执行 qk_rmsnorm_fused。但 Attention 默认 use_qk_norm=False，只有开启时才会创建 q_norm_weight / k_norm_weight；现有多处 Attention(...) 构造没有传 use_qk_norm。这些模型一旦配置 v_head_dim != head_dim，这里会把 None 作为 Triton 指针传入，qk_rmsnorm_fused_kernel 随后 tl.load(q_weight_ptr + ...) 会直接失败。建议把“需要外部 rope/write_cache”和“需要 q/k norm”拆开：只有权重存在或 layer.use_qk_norm 为真时才跑 fused norm；没有 q/k norm 的模型仍应只做 RoPE/write_cache。

[PaddlePaddle-bot]

这个新增用例仍然设置 v_head_dim=2 且 head_dim=2，因此不会覆盖本 PR 最关键的 qkdim != vdim 分支：V shard size、param offset、shared KV slice 等仍按旧路径通过。建议至少加入 v_head_dim != head_dim（例如 head_dim=2, v_head_dim=3）的 fused/split load 断言，验证 V 段和后续 offset/gate 不重叠。