shell-nlp/gpt_server

gpt_server是一个用于生产级部署LLMs、Embedding、Reranker、ASR、TTS、文生图、图片编辑和文生视频的开源框架。

49
/ 100
Emerging

This project helps you take various AI models, like those for generating text, converting speech to text, or creating images, and make them easily accessible through a standard interface. It takes inputs such as text prompts, audio files, or images, and delivers outputs like generated text, transcribed audio, or new images. Anyone who needs to integrate advanced AI capabilities into their applications or workflows, without getting deep into the technical complexities of each individual AI model, would find this useful.

246 stars.

Use this if you need a unified way to deploy and manage different AI models (like large language models, image generators, or speech processors) for your applications, allowing them to be called using a familiar OpenAI-compatible interface.

Not ideal if you only need to run a single, simple AI model occasionally or prefer to manage each model's deployment individually without a unified serving layer.

AI-integration content-generation speech-processing image-processing text-moderation
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

246

Forks

21

Language

Python

License

Apache-2.0

Last pushed

Mar 05, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/shell-nlp/gpt_server"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.