uccl-project/uccl

uccl

✅ Recently maintained

UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)

1,566Stars
187Forks
+117-day stars

C++ · Apache-2.0 · Last push 2026-11-03

Official repository & installation ↗
aiallreduceamdbroadcomcollectivecudagpuhpcllmnetworking

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2025-09-292026-11-03
View historical data
DateStars
2026-10-051,532
2026-10-061,532
2026-10-071,533
2026-10-081,533
2026-10-091,535
2026-10-101,537
2026-10-111,537
2026-10-121,537
2026-10-131,538
2026-10-141,538
2026-10-151,541
2026-10-161,541
2026-10-171,543
2026-10-181,544
2026-10-191,544
2026-10-201,547
2026-10-211,549
2026-10-221,551
2026-10-231,551
2026-10-241,551
2026-10-251,553
2026-10-261,555
2026-10-271,556
2026-10-281,558
2026-10-291,560
2026-10-301,560
2026-10-311,560
2026-11-011,560
2026-11-021,564
2026-11-031,566

Get the project

git clone https://github.com/uccl-project/uccl.git

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

vllm

High-throughput, memory-efficient LLM inference and serving engine that lets developers deploy models faster without building serving infrastructure.

★ 96,180sglang

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

★ 38,386