NAME

Langertha::Engine::SGLang - SGLang inference server

VERSION

version 0.307

SYNOPSIS

use Langertha::Engine::SGLang;

my $sglang = Langertha::Engine::SGLang->new(
    url   => 'http://localhost:30000/v1',
    model => 'Qwen/Qwen2.5-7B-Instruct',
);

print $sglang->simple_chat('Say something nice');

DESCRIPTION

Adapter for SGLang's OpenAI-compatible endpoint. SGLang is typically exposed as /v1/chat/completions with optional tool-calling support depending on model/backend setup.

Only url is required. Use the full /v1 base URL. No API key is required for local setups.

THIS API IS WORK IN PROGRESS

SEE ALSO

• https://docs.sglang.ai/ - SGLang documentation

• Langertha::Engine::OpenAIBase - Base class for OpenAI-compatible engines

• Langertha::Role::Tools - MCP tool calling interface

• Langertha::Engine::vLLM - Similar self-hosted OpenAI-compatible engine

SUPPORT

Issues

Please report bugs and feature requests on GitHub at https://github.com/Getty/langertha/issues.

CONTRIBUTING

Contributions are welcome! Please fork the repository and submit a pull request.

AUTHOR

Torsten Raudssus <torsten@raudssus.de> https://raudss.us/

COPYRIGHT AND LICENSE

This software is copyright (c) 2026 by Torsten Raudssus.

This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself.