[Cherry-Pick] [FDConfig] Unify num_experts_per_tok to moe_k in ModelConfig for MoE model compatibility(#7509)

[xyxinyang]

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)

Unify num_experts_per_tok to moe_k in ModelConfig for MoE model compatibility. This enables R3 support for models like Qwen3VLMOE, DeepSeek V3, and other MoE models that use num_experts_per_tok instead of moe_k in their config.

Modifications

• Added unified field mapping in ModelConfig (fastdeploy/config.py)

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.
• 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.

[paddle-bot]

Thanks for your contribution!

[PaddlePaddle-bot]

🤖 AI Code Review | 2026-04-21 12:16:15

📋 Review 摘要

PR 概述：将 MoE 模型 config 中的 num_experts_per_tok 统一映射到 moe_k，使 ERNIE 4.5 MoE 等使用 moe_k 的模型能兼容 Qwen3VLMOE、DeepSeek V3 等使用 num_experts_per_tok 的模型配置。
变更范围：fastdeploy/config.py — ModelConfig.override_name_from_config() 方法
影响面 Tag：[FDConfig]

问题

未发现阻塞性问题。

总体评价

变更简洁、安全，与现有的 num_experts → moe_num_experts、n_routed_experts → moe_num_experts 等字段映射模式保持一致。hasattr 双重检查保证了向后兼容性——仅在 config.json 包含 num_experts_per_tok 且缺少 moe_k 时才做映射，不会影响已有模型的加载行为。

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (release/2.6@f4f7760). Learn more about missing BASE report.

Additional details and impacted files

@@              Coverage Diff               @@
##             release/2.6    #7517   +/-   ##
==============================================
  Coverage               ?   73.57%           
==============================================
  Files                  ?      376           
  Lines                  ?    53000           
  Branches               ?     8280           
==============================================
  Hits                   ?    38995           
  Misses                 ?    11260           
  Partials               ?     2745           

Flag	Coverage Δ
GPU	73.57% <100.00%> (?)

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

☔ 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.