Rank #9,171 534 starsPython

sarathi-serve

by microsoft (organization)

A low-latency & high-throughput serving engine for LLMs (description from the project’s GitHub page)

Repository facts

Stars: 534
Forks: 68
Open issues and pull requests: 17
Primary language: Python
License: Apache License 2.0 (Apache-2.0)
Owner: microsoft · Organization
Created: Nov 2, 2023
Last push: Jan 8, 2026

Topics

Rank #9,171 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Add this badge to your README

Ranked #9,171 in AI on GitHub Shows this repository’s rank in AI on GitHub and links back to this page. Ranks are by stars and change when the list is refreshed. The badge is not an endorsement or a rating. About the badges

Markdown (for a README)

[![Ranked #9,171 in AI on GitHub](https://unitedstatesofamericasuperintelligence.com/badges/github/microsoft--sarathi-serve.svg)](https://unitedstatesofamericasuperintelligence.com/github/microsoft--sarathi-serve/)

HTML

<a href="https://unitedstatesofamericasuperintelligence.com/github/microsoft--sarathi-serve/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/github/microsoft--sarathi-serve.svg" alt="Ranked #9,171 in AI on GitHub" height="20"></a>

Projects that share this one’s GitHub topics.

Rank 43: vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
94,068 starsPythonApache-2.0Last push Oct 18, 2026
Rank 768: bigscience-workshop/petals
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
10,639 starsPythonMITLast push Sep 7, 2024
Rank 2,609: pytorch/ao
PyTorch native quantization for training and inference
3,005 starsPythonOther licenseLast push Oct 16, 2026
Rank 3,021: X-PLUG/mPLUG-Owl
mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
2,539 starsPythonMITLast push Apr 2, 2025
Rank 4,833: GradientHQ/parallax
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
1,397 starsPythonApache-2.0Last push Jul 1, 2026
Rank 6,577: explosion/curated-transformers
🤖 A PyTorch library of curated Transformer models and their composable components
890 starsPythonMITLast push Apr 17, 2024

Repository facts

Topics

Add this badge to your README

Related projects

Rank 43: vllm-project/vllm

Rank 768: bigscience-workshop/petals

Rank 2,609: pytorch/ao

Rank 3,021: X-PLUG/mPLUG-Owl

Rank 4,833: GradientHQ/parallax

Rank 6,577: explosion/curated-transformers

Support Us