kvcache-ai/Mooncake

Mooncake

✅ Recently maintained

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

6,958Stars
1,426Forks
+657-day stars

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

Official repository & installation ↗
inferencekvcachellmrdmasglangvllmdisaggregationtokenspeedreinforcement-learningtrt-llm

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
2026-10-056,709
2026-10-066,714
2026-10-076,724
2026-10-086,734
2026-10-096,741
2026-10-106,753
2026-10-116,761
2026-10-126,771
2026-10-136,780
2026-10-146,793
2026-10-156,803
2026-10-166,810
2026-10-176,816
2026-10-186,824
2026-10-196,834
2026-10-206,844
2026-10-216,854
2026-10-226,864
2026-10-236,869
2026-10-246,873
2026-10-256,879
2026-10-266,889
2026-10-276,903
2026-10-286,912
2026-10-296,922
2026-10-306,930
2026-10-316,935
2026-11-016,946
2026-11-026,953
2026-11-036,958

Get the project

git clone https://github.com/kvcache-ai/Mooncake.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.

★ 38,386litellm

Call 100+ LLM APIs using the OpenAI input/output format.

★ 62,604