GitHub repo leaderboard by stars, growth rate and activity.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
Optimizing inference proxy for LLMs
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective. | Python | 43,083 | last pushed Yesterday | |
| 2 | A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU. | C | 7,382 | last pushed 2 weeks ago | |
| 3 | Optimizing inference proxy for LLMs | Python | 4,262 | last pushed 2 months ago |
All · 11,474