ai-decentralized / BloomBee
Decentralized LLMs fine-tuning and inference with offloading
Why this job: says: fine tuning
What it does
- Tensor offloading. reduces per-node memory consumption so each peer can host more layers, shrinking the total number of network hops.
- Speculative decoding over internet. reduces communication frequency by sending multiple draft tokens per round-trip.
- Lossless activation-compression. shrinks the bytes transferred per activation, without accuracy loss.
- Micro-batch pipelining. overlaps communication with computation to hide network latency.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 19 days ago
- Stars
- 135
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 98% of the code
Is it looked after?
- Contributors
- 4
- Last 90 days
- Issues
- 67% closed
- 3 still open
- Pull requests
- 53 merged
- 4 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 |
|---|---|---|---|---|
| Lightning-AI / pytorch-lightning | 31,447 | 49 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 98%
- Jinja 2%
- Dockerfile <1%
- Shell <1%
Topics
- deep-learning
- distributed-systems
- llama
- machine-learning
- pipeline-parallelism
- pytorch
- tensor-parallelism
Project record
- JobFine-tuning
- StatusListed
- Commits99
- Forks35
- Watching11
- Stars in 28 days+2
- CreatedJan 23, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026