sarathi-serve

A low-latency & high-throughput serving engine for LLMs

microsoft/sarathi-serve

View on GitHub ↗

A low-latency & high-throughput serving engine for LLMs

sarathi-serve grew +1.5% in the last 30 days, ranks 218th of 496 in Local Runtime / Inference Engine, last commit 291 days ago.

Star trajectory

127 days tracked
2026-06-20535 stars today2026-10-26
Momentum

+1.5% in 30d, below the Local Runtime / Inference Engine median of +1.7%.

Maintenance

Last commit 291 days ago, staler than the median of 6d.

How it compares in Local Runtime / Inference Engine

sarathi-serve
535
stars
+1.5% 30d
commit 291 days ago
Local Runtime / Inference Engine median
409.5
stars
+1.7% 30d
commit ~6d ago
Leader · ollama
184.8k
stars
+1.7% 30d
commit today

Ranked 218th of 496 by stars.

Language
Python
License
Apache License 2.0
Contributors
10
Forks
68
Watchers
7
Open issues
10
Releases
0
Created
2023-11-02
Stars this week
+1

You've seen where sarathi-serve stands today.

Get the moves before everyone else: the 5 Local Runtime / Inference Engine repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain sarathi-serve?

Claim this page to add your own call-to-action.

Claim this page