OrbitInfra / OrbitKV
OrbitKV: KV cache for vLLM and SGLang. Reuse prefixes across DRAM, SSD and peer hosts, built in Rust on OrbiTE.
Why this job: topics: llm-inference, vllm, llm-serving
What it does
- Reuse beyond GPU memory. retain compatible prefixes in DRAM and optional
- Share cache capacity. attach local engines to a Manager or discover peer
- Keep ownership explicit. hold sources, destinations and registrations until
- Describe recovery requirements. compile supported prefix, window and
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit today
- Stars
- 277
- +4 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Rust
- 58% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 67% closed
- 1 still open
- Pull requests
- 320 merged
- 0 waiting
- Releases
- None
- Never published
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| liguodongiot / llm-action | 25,266 | 26 days ago | Apache-2.0 | No downloads |
| gpustack / gpustack | 6,004 | today | Apache-2.0 | No downloads |
| novitalabs / pegaflow | 221 | 6 days ago | Apache-2.0 | Linux |
More: languages, topics and project record
Languages
- Rust 58%
- Python 41%
- Cuda 1%
- C++ <1%
Topics
- rust
- llm-inference
- kv-cache
- attention
- memory-management
- orbitkv
- sglang
- vllm
- kv-cache-offloading
- llm-serving
- prefix-caching
- orbite
Project record
- JobLocal LLMs
- StatusListed
- Commits1,877
- Forks18
- Watching10
- Stars in 28 days+4
- CreatedMar 31, 2025
- First seen by usNov 7, 2026
- CheckedNov 9, 2026