[Cherry-Pick][TI-consistent] support quant use pow2scale(#7308)

[liuruyan]

Motivation

针对训推一致性对齐需求，在FD中支持quant 选择pow2scale模式，通过FD_FP8_QUANT_WITH_POW2SCALE控制

Modifications

新增FD_FP8_QUANT_WITH_POW2SCALE参数

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.

[paddle-bot]

Thanks for your contribution!

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (release/2.6@42b0f59). Learn more about missing BASE report.

Additional details and impacted files

@@              Coverage Diff               @@
##             release/2.6    #7310   +/-   ##
==============================================
  Coverage               ?   73.85%           
==============================================
  Files                  ?      376           
  Lines                  ?    52960           
  Branches               ?     8268           
==============================================
  Hits                   ?    39112           
  Misses                 ?    11114           
  Partials               ?     2734           

Flag	Coverage Δ
GPU	73.85% <ø> (?)

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.

[fastdeploy-bot]

🤖 AI Code Review | 2026-04-11

📋 Review 摘要

PR 概述：新增 FD_FP8_QUANT_WITH_POW2SCALE 环境变量，支持 FP8 量化使用 pow2scale 模式，用于训推一致性对齐。

变更范围：fastdeploy/envs.py、model_executor/layers/moe/、model_executor/layers/quantization/

影响面 Tag：[Quantization] [RL]

📝 PR 规范检查

标题 Tag 问题：标题使用了 [Cherry-Pick][TI-consistent]，其中 [TI-consistent] 不在官方 Tag 列表中。根据 PR 描述中的 "train-infer consistency" 和 FD_ENABLE_RL 相关性，应使用 [RL] Tag。

标题建议：

• [Cherry-Pick][Quantization][RL] support quant use pow2scale(#7308)
• [Cherry-Pick][RL][Quantization] support quant use pow2scale(#7308)

描述建议：

• ✅ Motivation 已填写
• ✅ Modifications 已填写
• ⚠️ 建议补充 Usage 说明（如何设置环境变量）
• ⚠️ Checklist 中的 "Add at least a tag in the PR title" 未勾选，当前 Tag 不符合规范

问题

级别	文件	概述
🟡 建议	PR 标题	[TI-consistent] 不在官方 Tag 列表中，应使用 [RL]

未发现阻塞性问题。

总体评价

代码逻辑正确，环境变量定义和使用方式符合项目规范。新增的 FD_FP8_QUANT_WITH_POW2SCALE 通过 or 逻辑与原有配置组合，提供了灵活的量化模式控制。建议修正 PR 标题中的 Tag 并补充 Usage 说明。