[Models] fix fleet model fallback ep init

[xiaoguoguo626807]

Motivation

修复 --model-impl paddlefleet fallback 场景下生成模型校验与 Expert Parallel 初始化状态复用问题，避免 PaddleFleet 初始化时使用不匹配的 TP/EP parallel state。

Modifications

• fastdeploy/config.py：允许 model_impl=paddlefleet 在 runner_type=generate 且模型未被 FastDeploy 原生 registry 标记为生成模型时继续走 fallback。
• fastdeploy/model_executor/models/paddleformers/base_fleet.py：为 PaddleFleet fallback 配置 CPU 初始化和跳过参数初始化，并在 fleet.init() 前重置 Paddle Fleet hybrid topology。

Usage or Command

N/A

Accuracy Tests

N/A

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.
• [x ] 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

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@f161fea). Learn more about missing BASE report.

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #8039   +/-   ##
==========================================
  Coverage           ?   67.50%           
==========================================
  Files              ?      475           
  Lines              ?    66661           
  Branches           ?    10284           
==========================================
  Hits               ?    45002           
  Misses             ?    18788           
  Partials           ?     2871           

Flag	Coverage Δ
GPU	77.48% <100.00%> (?)
XPU	6.98% <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 | 2026-06-12 21:32:45

CI报告基于以下代码生成（30分钟更新一次）:
PR commit: f5a72c4 | Merge base: f161fea (branch: develop)

---

1 Required任务 : 9/10 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	38	4	0	0	0

任务	错误类型	置信度	日志
Run FastDeploy Unit Tests and Coverage / run_tests_with_coverage	PR问题	高	Job

2 失败详情

🔴 Run FastDeploy Unit Tests and Coverage / run_tests_with_coverage — PR问题（置信度: 高）

错误类型: PR问题 | 置信度: 高
分析器: 通用分析(fallback)
失败用例:

用例	错误摘要
tests/model_executor/fallback/test_fallback_fleet_model_coverge.py::TestInitPaddlefleetParallelState::test_seed_assertion_error_is_silenced	initialize_model_parallel 触发 PaddleFleet 全局 memory buffer 已初始化断言

关键日志:

tests/model_executor/fallback/test_fallback_fleet_model_coverge.py:1070: model._init_paddlefleet_parallel_state(fd_config)
fastdeploy/model_executor/models/paddleformers/base_fleet.py:422: parallel_state.initialize_model_parallel(hcg)
/usr/local/lib/python3.10/dist-packages/paddlefleet/parallel_state.py:426: assert _GLOBAL_MEMORY_BUFFER is None
AssertionError: global memory buffer is already initialized

• 根因摘要: PR改为初始化PaddleFleet时未重置全局缓冲
  PR 在 fastdeploy/model_executor/models/paddleformers/base_fleet.py:420-422 删除了原先 TP=1 手动建组/TP size mismatch 分支，改为只要 _TENSOR_MODEL_PARALLEL_GROUP is None 就调用 parallel_state.initialize_model_parallel(hcg)。失败用例将 _TENSOR_MODEL_PARALLEL_GROUP 置空后，本应验证 model_parallel_cuda_manual_seed 的 AssertionError 会被 base_fleet.py:428-431 吞掉，但新逻辑先进入 initialize_model_parallel，被 PaddleFleet 已存在的 _GLOBAL_MEMORY_BUFFER 断言拦截，seed 分支没有执行。因此这是本 PR 的 base_fleet.py 初始化逻辑变更直接触发的单测失败。

修复建议:

1. 在 base_fleet.py 调用 parallel_state.initialize_model_parallel(hcg) 前，使用 PaddleFleet/Paddle 的正式 reset/destroy API 清理已有 parallel_state 全局状态，至少要覆盖 _GLOBAL_MEMORY_BUFFER；若 TP=1 不需要重新初始化 model parallel，则保留或恢复原 TP=1 手动建组路径。
2. 若新初始化语义是预期行为，同步更新 tests/model_executor/fallback/test_fallback_fleet_model_coverge.py:1049 附近的用例，在只验证 seed 断言吞掉时 mock 或重置 ps.initialize_model_parallel 相关全局状态，并清理仍描述旧 TP=1 分支的断言。

关联变更: fastdeploy/model_executor/models/paddleformers/base_fleet.py:399-422；PR 删除旧 TP=1/mismatch 分支并新增 fleet 状态重置后统一初始化。

[PaddlePaddle-bot]

🤖 Paddle-CI-Agent | pr_review | 2026-06-16 17:38:00

📋 Review 摘要

PR 概述：修复 --model-impl paddlefleet fallback 的生成模型校验与 PaddleFleet EP/TP 初始化状态复用问题。
变更范围：fastdeploy/config.py、fastdeploy/model_executor/models/paddleformers/base_fleet.py
影响面 Tag：[Models] [FDConfig]

问题

级别	文件	概述
🔴 Bug	fastdeploy/model_executor/models/paddleformers/base_fleet.py:431	TP=1 手工重建 PaddleFleet TP group 时未同步重置 global ranks，仍可能复用旧拓扑状态

历史 Findings 修复情况

Finding	问题	状态
F1	旧 TP group 拓扑过期时仍可能被保留	⚠️ 仍存在

📝 PR 规范检查

标题和描述结构已按上次建议补齐；未发现需要阻塞本次修复的规范问题。Checklist 中 - [x ] Add unit tests 不是合法 checkbox，建议按实际测试情况改成合法的 [ ] 或 [x]。

总体评价

paddlefleet fallback 的配置放行方向合理，但 PaddleFleet parallel_state 的重置仍不完整。请修复 TP=1 分支的 global ranks 同步，并同步检查 same-size stale TP group 是否应强制用新的 HCG 重新初始化。

[PaddlePaddle-bot]

🔴 Bug TP=1 的手工重建分支只替换了 _TENSOR_MODEL_PARALLEL_GROUP，没有同步重置对应的 global ranks 状态。

这个函数前面刚把 HCG/parallel context 置空，目标是避免 PaddleFleet 复用旧拓扑；但当 expected_tp_size == 1 时，这里只创建新 group，删除了原先同步写 _TENSOR_MODEL_PARALLEL_GLOBAL_RANKS = [current_rank] 的逻辑。如果进程里已有上一次初始化留下的 global ranks，PaddleFleet parallel_state 会出现 group 与 global ranks 不一致，后续依赖 tensor-parallel rank/global ranks 的 sharded state 或随机种子初始化仍可能按旧拓扑运行。

建议修复方式：在 TP=1 分支同时设置与新 group 匹配的 global ranks，例如先保存 current_rank = dist.get_rank()，然后同时写：

parallel_state._TENSOR_MODEL_PARALLEL_GROUP = dist.new_group(ranks=[current_rank])
parallel_state._TENSOR_MODEL_PARALLEL_GLOBAL_RANKS = [current_rank]

如果 PaddleFleet 提供 destroy/reset API，更稳妥的是先清空 TP 相关 parallel_state 后再用新的 HCG 初始化。

[gongshaotian]

LGTM