Skip to content

>awesome-alternatives

Search the catalog

Browse About Add a tool

Language

English Français Español Deutsch Português (Brasil)日本語 Bahasa Indonesia

Home
Local model runtimes
SGLang

alternative to vLLM, ChatGPT, Claude

SGLang

Loading the README

v0.5.212026-10-02779 PRs from 227 contributors.
v0.5.202026-09-18713 PRs from 237 contributors.
v0.5.192026-09-05786 PRs from 214 contributors.
v0.5.182026-08-22710 PRs from 212 contributors.
v0.5.172026-08-08582 PRs from 194 contributors.

unsigned The latest release, v0.5.21, carries no signature GitHub could verify.

Loading the security report

vLLMGPU serving engine for open-weight models behind an OpenAI-compatible API.Full replacement
ChatGPTServes open-weight models behind an OpenAI-compatible API, tuned for GPU throughput.Partial
ClaudeServes open-weight models behind an OpenAI-compatible API.Partial

About

SGLang is a high-performance serving framework for large language models and multimodal models.

PythonLocal model runtimesApache-2.0

Owner: sgl-project organisation
Stars: 37k
Forks: 9.3k
Latest: v0.5.21
Last push: 2026-10-06
Terms: Open source
Self-hosted: Yes
Created: 2024, 2 years ago
Release cadence: about 14 days between releases
Active contributors: 161+ commit authors on the default branch in the last 90 days
Stars over 12 days: 2026-09-25 36,4292026-10-06 36,818

Read from GitHub on 2026-10-06.Entry last edited on 2026-09-25.

Compare SGLang and vLLM →

#attention#blackwell#cuda#deepseek#diffusion#glm#gpt-oss#inference

github.com/sgl-project/sglang ↗Website ↗Edit this entry Changes to SGLang (RSS)

Other tools in Local model runtimes

OllamaGo→
llama.cppC++→
vLLMPython→
LocalAIGo→
exoPython→
llamafileC++→
MLC LLMPython→
KTransformersPython→
TensorRT-LLMPython→
XinferencePython→
LMDeployPython→
mistral.rsRust→
llama-swapGo→
LemonadeC++→
GPUStackPython→
RamaLamaPython→
TabbyAPIPython→

Catalog CC BY-SA, code AGPL, data from GitHub, every night

How it works What changed RSS feed Contact Legal notice Privacy GitHub ↗