Zefan-Cai / KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
Why this job: works in the areas we cover, but does not say which job it does
What it does
KVCache-Factory is a unified playground for KV cache compression, retrieval, merging, and quantization methods for long-context LLM inference. It started from PyramidKV and now includes multiple KV cache baselines under one evaluation interface.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 3 months ago
- Stars
- 1,394
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 96% closed
- 2 still open
- Pull requests
- 19 merged
- 2 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| thu-nics / C2C | 774 | 15 days ago | Apache-2.0 | No downloads |
| raymin0223 / mixture_of_recursions | 652 | 54 days ago | Apache-2.0 | No downloads |
| lordx64 / phantom-kv | 274 | 52 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 99%
- Shell 1%
- Cuda <1%
- C <1%
Topics
- kv-cache
- kv-cache-compression
- llm
Project record
- JobOther AI tools
- StatusListed
- Commits158
- Forks181
- Watching92
- Stars in 28 days+8
- CreatedJun 5, 2024
- First seen by usNov 7, 2026
- CheckedNov 8, 2026