kvcache-ai / Mooncake
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
Why this job: topics: vllm, inference
What it does
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. Under real workloads, Mooncake’s innovative architecture enables Kimi to handle 75% more requests while adhering to SLOs.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit today
- Stars
- 7,013
- +51 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- Linux
- From the latest release
- Latest version
- v0.3.14
- Released 7 days ago
- Built with
- C++
- 64% of the code
Is it looked after?
- Contributors
- 65
- Last 90 days
- Issues
- 71% closed
- 388 still open
- Pull requests
- 2,786 merged
- 591 waiting
- Releases
- 36
- 17 in the last year
- Contributing guide (opens in new tab)
- No security policy
- Code of conduct (opens in new tab)
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| ovg-project / kvcached | 2,036 | yesterday | Apache-2.0 | No downloads |
| gpustack / gpustack | 6,005 | today | Apache-2.0 | No downloads |
| SemiAnalysisAI / InferenceX | 2,016 | today | Apache-2.0 | No downloads |
More: download files, languages, topics, project record and preview image
Languages
- C++ 64%
- Rust 18%
- Python 12%
- Shell 2%
Topics
- inference
- kvcache
- llm
- rdma
- sglang
- vllm
- disaggregation
- tokenspeed
- reinforcement-learning
- trt-llm
Project record
- JobLocal LLMs
- StatusListed
- Commits2,676
- Forks1,458
- Watching47
- Stars in 28 days+245
- CreatedJun 25, 2024
- First seen by usNov 7, 2026
- CheckedNov 10, 2026