[Optimization]Change default workers and max-concurrency when launch api-server

[K11OntheBoat]

Motivation

API-Server 启动服务时，将workers默认从1改为4，服务最大concurrency同步改为2048. 避免了GPU 运行快，但是请求不足的性能瓶颈. Blackwell架构，长输入短输出数据，512并发场景，GLM4.5-Air模型TPS提升1.74倍.
multi_api_server中这两个参数保持不变.

Modifications

API-Server 启动服务时，将workers默认从1改为4，服务最大concurrency同步改为2048.

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 | 2026-04-17 12:15 CST

📋 Review 摘要

PR 概述：将 API-Server 的 workers 默认值从 1 调整为 4，max-concurrency 从 512 调整为 2048，以避免 GPU 运行快但请求不足的性能瓶颈；multi_api_server 模式下保持原值不变。
变更范围：entrypoints/api_server.py、entrypoints/openai/utils.py
影响面 Tag：APIServer

问题

级别	文件	概述
🟡 建议	openai/utils.py:344	环境变量读取方式与项目惯例不一致，建议使用 envs 模块

总体评价

变更逻辑清晰，通过环境变量 FD_ENABLE_MULTI_API_SERVER 区分单机和多机模式分别设置默认值，思路合理。建议将环境变量读取方式统一为项目已有的 envs 模块，保持代码风格一致性。

[PaddlePaddle-bot]

🟡 建议 环境变量读取方式与项目惯例不一致

项目中其他地方统一使用 fastdeploy.envs 模块访问 FD_ENABLE_MULTI_API_SERVER（如 envs.FD_ENABLE_MULTI_API_SERVER），而这里直接使用 os.environ.get() 读取。虽然功能等价，但不一致的读取方式在未来维护时可能导致混淆（例如 envs 模块增加缓存或校验逻辑时，这里不会受益）。

建议改为使用已导入的 envs 模块：

_is_multi_server = envs.FD_ENABLE_MULTI_API_SERVER

注意：文件顶部已有 import fastdeploy.envs as envs（第 31 行），无需额外导入。

[codecov-commenter]

Codecov Report

❌ Patch coverage is 75.00000% with 1 line in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@6847891). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
fastdeploy/entrypoints/api_server.py	0.00%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #7457   +/-   ##
==========================================
  Coverage           ?   73.26%           
==========================================
  Files              ?      398           
  Lines              ?    54976           
  Branches           ?     8613           
==========================================
  Hits               ?    40279           
  Misses             ?    12007           
  Partials           ?     2690           

Flag	Coverage Δ
GPU	73.26% <75.00%> (?)

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.

[EmmonsCurse]

✅ Cherry-pick successful! Created PR: #7516