thu-nics / C2C
[ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"
Why this job: works in the areas we cover, but does not say which job it does
What it does
Cache-to-Cache (C2C) enables Large Language Models to communicate directly through their KV-Caches, bypassing text generation. By projecting and fusing KV-Caches between models, C2C achieves 8.5–10.5% higher accuracy than individual models and 3.0–5.0% better performance than text-based communication, with 2.0× speedup in latency.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 15 days ago
- Stars
- 774
- +3 this week
- Licence
- Apache-2.0
- 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
- 1
- Last 90 days
- Issues
- 93% closed
- 1 still open
- Pull requests
- 1 merged
- 6 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Zefan-Cai / KVCache-Factory | 1,394 | 3 months ago | MIT | 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%
- Jupyter Notebook 1%
- Shell <1%
- Jinja <1%
Topics
- kv-cache
- llm
- multi-agent
Project record
- JobOther AI tools
- StatusListed
- Commits35
- Forks98
- Watching11
- Stars in 28 days+47
- CreatedOct 3, 2025
- First seen by usNov 7, 2026
- CheckedNov 9, 2026