FastFlowLM
✅ Recently maintainedRun LLMs on AMD Ryzen™ AI NPUs in minutes; purpose-built and deeply optimized for the AMD NPUs.
2,011Stars
172Forks
+227-day stars
C++ · License unverified · Last push 2026-11-02
Official repository & installation ↗Star history
2025-09-292026-11-02
View historical data
| Date | Stars |
|---|---|
| 2026-10-04 | 1,922 |
| 2026-10-05 | 1,925 |
| 2026-10-06 | 1,926 |
| 2026-10-07 | 1,931 |
| 2026-10-08 | 1,934 |
| 2026-10-09 | 1,939 |
| 2026-10-10 | 1,941 |
| 2026-10-11 | 1,944 |
| 2026-10-12 | 1,945 |
| 2026-10-13 | 1,947 |
| 2026-10-14 | 1,953 |
| 2026-10-15 | 1,954 |
| 2026-10-16 | 1,956 |
| 2026-10-17 | 1,960 |
| 2026-10-18 | 1,964 |
| 2026-10-19 | 1,966 |
| 2026-10-20 | 1,970 |
| 2026-10-21 | 1,975 |
| 2026-10-22 | 1,977 |
| 2026-10-23 | 1,980 |
| 2026-10-24 | 1,984 |
| 2026-10-25 | 1,988 |
| 2026-10-26 | 1,992 |
| 2026-10-27 | 1,994 |
| 2026-10-28 | 1,999 |
| 2026-10-29 | 2,004 |
| 2026-10-30 | 2,006 |
| 2026-10-31 | 2,009 |
| 2026-11-01 | 2,011 |
| 2026-11-02 | 2,011 |
Get the project
git clone https://github.com/ROCm/FastFlowLM.git
Related projects & alternative candidates
Related domains do not imply feature parity. Review official documentation and licenses.
ollama
Run DeepSeek, Qwen, Gemma and other LLMs locally with one command, plus model management and an API.
★ 185,625vllmHigh-throughput, memory-efficient LLM inference and serving engine that lets developers deploy models faster without building serving infrastructure.
★ 96,103sglangSGLang is a high-performance serving framework for large language models and multimodal models.
★ 38,359