[Speculative Decoding] Remove arctic_inference deps

[Deleter-D]

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.

[paddle-bot]

Thanks for your contribution!

[fastdeploy-bot]

🤖 AI Code Review | 2026-04-08

📋 Review 摘要

PR 概述：将 arctic_inference 从硬依赖改为可选依赖，仅在 Suffix Decoding 功能使用时按需安装

变更范围：fastdeploy/spec_decode/suffix.py、requirements.txt

影响面 Tag：[Speculative Decoding]

---

📝 PR 规范检查

1. 标题：符合规范，包含 [Speculative Decoding] 标签
2. 描述：## Motivation 和 ## Modifications 段落为空，建议填写

描述模板（可直接复制）：

## Motivation
将 `arctic_inference` 从硬依赖改为可选依赖，减少不必要的依赖安装。只有使用 Suffix Decoding 功能时才需要安装此包。

## Modifications
- 从 requirements.txt 中移除 arctic_inference 硬依赖
- 更新 SuffixProposer 的错误提示，明确安装命令和版本号

---

问题

级别	文件	概述
🟡 建议	fastdeploy/spec_decode/suffix.py:46	版本号不一致：错误信息指定 0.1.2，但原依赖是 0.1.3

---

📄 文档建议（本次 PR 未包含）

虽然本次 PR 未修改文档文件，但建议后续更新文档说明 Suffix Decoding 的依赖安装：

• docs/features/speculative_decoding.md: 在 "🌲 Using Suffix Decoding" 章节添加依赖说明
• docs/zh/features/speculative_decoding.md: 在 "🌲 使用后缀解码" 章节添加依赖说明

建议添加内容：

> Note: Suffix Decoding requires the `arctic-inference` package. Install it with:
> ```bash
> pip install arctic-inference==<正确版本号>
> ```

---

总体评价

将 arctic_inference 从硬依赖改为可选依赖的方案合理，使用 try-except 导入模式优雅处理缺失依赖的情况。但存在版本号不一致的问题，建议确认正确的版本号并统一更新错误提示信息。

[fastdeploy-bot]

🟡 建议 版本号不一致：错误信息中指定的是 arctic-inference==0.1.2，但原 requirements.txt 使用的是 arctic_inference-0.1.3 版本。请确认正确的版本号并保持一致。

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@8496ec7). Learn more about missing BASE report.

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #7231   +/-   ##
==========================================
  Coverage           ?   73.59%           
==========================================
  Files              ?      383           
  Lines              ?    53493           
  Branches           ?     8375           
==========================================
  Hits               ?    39367           
  Misses             ?    11381           
  Partials           ?     2745           

Flag	Coverage Δ
GPU	73.59% <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.