rbiswasfc

File: README.md

SGLang Documentation

We recommend new contributors start from writing documentation, which helps you quickly understand SGLang codebase. Most documentation files are located under the docs/ folder. We prefer Jupyter Notebooks over Markdown so that all examples can be executed and validated by our docs CI pipeline.

Docs Workflow

Install Dependency

rbiswasfc

README.md

vLLM documents

Build the docs

# Install dependencies.
pip install -r requirements-docs.txt

rbiswasfc

Quick Start

OpenRouter provides an OpenAI-compatible completion API to 0 models & providers that you can call directly, or using the OpenAI SDK. Additionally, some third-party SDKs are available.

In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.

Using the OpenAI SDK

from openai import OpenAI

rbiswasfc

rbiswasfc

rbiswasfc

rbiswasfc

rbiswasfc

AUTOGENERATED! DO NOT EDIT! File to edit: ../00_core.ipynb.

%% auto 0

all = ['empty', 'model_types', 'all_models', 'models', 'models_aws', 'models_goog', 'pricing', 'find_block', 'contents', 'usage', 'mk_msgs', 'Client', 'mk_tool_choice', 'call_func', 'mk_funcres', 'mk_toolres', 'Chat', 'img_msg', 'text_msg', 'mk_msg']

%% ../00_core.ipynb

import inspect, typing, mimetypes, base64, json from collections import abc

rbiswasfc

name: nbdev
channels:
  - pytorch
  - fastai
  - huggingface
  - conda-forge
  - defaults
dependencies:
  - python=3.10
  - pandas

rbiswasfc

from fasthtml.common import *
from fasthtml.oauth import HuggingFaceClient, redir_url

# Auth client
client = HuggingFaceClient(os.getenv("HF_CLIENT_ID"), os.getenv("HF_API_SECRET"))

app = FastHTML()
redir_path = "/auth/callback"