sgl-project/sglang

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

100
/ 100
Verified

Implements RadixAttention for prefix caching, zero-overhead batch scheduling, and prefill-decode disaggregation to optimize inference latency and throughput. Supports tensor/pipeline/expert/data parallelism with structured output constraints via compressed finite state machines. Runs across NVIDIA, AMD, Intel, and Google TPU hardware with native integrations for reinforcement learning and post-training workflows.

24,410 stars and 45,662,765 monthly downloads. Used by 5 other packages. Actively maintained with 962 commits in the last 30 days. Available on PyPI.

Maintenance 25 / 25
Adoption 25 / 25
Maturity 25 / 25
Community 25 / 25

How are scores calculated?

Stars

24,410

Forks

4,799

Language

Python

License

Apache-2.0

Last pushed

Mar 13, 2026

Monthly downloads

45,662,765

Commits (30d)

962

Dependencies

64

Reverse dependents

5

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sgl-project/sglang"

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