raft
✅ Recently maintainedRAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
1,051Stars
256Forks
+37-day stars
Cuda · Apache-2.0 · Last push 2026-11-02
Official repository & installation ↗Star history
2025-09-292026-11-02
View historical data
| Date | Stars |
|---|---|
| 2026-10-04 | 1,042 |
| 2026-10-05 | 1,043 |
| 2026-10-06 | 1,043 |
| 2026-10-07 | 1,043 |
| 2026-10-08 | 1,043 |
| 2026-10-09 | 1,043 |
| 2026-10-10 | 1,044 |
| 2026-10-11 | 1,045 |
| 2026-10-12 | 1,046 |
| 2026-10-13 | 1,046 |
| 2026-10-14 | 1,046 |
| 2026-10-15 | 1,046 |
| 2026-10-16 | 1,046 |
| 2026-10-17 | 1,047 |
| 2026-10-18 | 1,047 |
| 2026-10-19 | 1,047 |
| 2026-10-20 | 1,047 |
| 2026-10-21 | 1,047 |
| 2026-10-22 | 1,047 |
| 2026-10-23 | 1,047 |
| 2026-10-24 | 1,048 |
| 2026-10-25 | 1,048 |
| 2026-10-26 | 1,048 |
| 2026-10-27 | 1,048 |
| 2026-10-28 | 1,048 |
| 2026-10-29 | 1,049 |
| 2026-10-30 | 1,049 |
| 2026-10-31 | 1,049 |
| 2026-11-01 | 1,051 |
| 2026-11-02 | 1,051 |
Get the project
git clone https://github.com/NVIDIA/raft.git
Related projects & alternative candidates
Related domains do not imply feature parity. Review official documentation and licenses.
LLMs-from-scratch
Step-by-step guide to building a GPT-like LLM from scratch in PyTorch.
★ 107,704vllmHigh-throughput, memory-efficient LLM inference and serving engine that lets developers deploy models faster without building serving infrastructure.
★ 96,161sglangSGLang is a high-performance serving framework for large language models and multimodal models.
★ 38,385