Run LLMs on AMD Ryzen™ AI NPUs in minutes; purpose-built and deeply optimized for the AMD NPUs.
Star History
Momentum
+48
STARS · LAST 30 DAYS
2
PER DAY
#138
MOST-STARRED C++
| Window | 7 days | 30 days | 90 days |
|---|---|---|---|
| Stars gained | +14 | +48 | +180 |
| Per day | 2 | 2 | 2 |
| Forks gained | +1 | +3 | +10 |
FastFlowLM gained 48 stars in the last 30 days, about 2 a day, and now has 1.9K. It is about 1 year old and has averaged roughly 1.9K stars a year. It ranks #138 among C++ repositories and #1,938 across all languages on GitHubRepo.
Trending Record
5
DAYS ON TRENDING
#555
BEST RANK
Sep 24, 2026
FIRST APPEARANCE
Active
STATUS TODAY
FastFlowLM has maintained a continuous presence across global trending indexes, peaking at #555. Below is the 30-day activity profile:
💡 Overview
FastFlowLM is an open-source project written in C++: Run LLMs on AMD Ryzen™ AI NPUs in minutes; purpose-built and deeply optimized for the AMD NPUs.
Engineered for speed, consistency, and developer ease, it solves common hurdles in amd, deepseek, llama. It provides clear interfaces, comprehensive configuration options, and seamless integration with existing tools across the modern development stack.
⚡ Key Features
Optimized execution pipeline written in C++ for predictable speed.
Zero-friction configuration with comprehensive sensible defaults out of the box.
Cross-platform runtime support across Linux, macOS, and Windows environments.
Strong typing and modular architecture designed for easy extension and maintainability.
Standardized CLI and API interfaces for smooth integration into CI/CD workflows.
Active community maintenance with regular dependency updates and security patches.
📥 Installation
$ git clone https://github.com/ROCm/FastFlowLM.git
cd FastFlowLM⚙ System Requirements
Platforms
- • macOS
- • Linux
- • Windows
Runtime & Dependencies
C++20 compliant compiler (GCC 11+, Clang 13+, MSVC)
Architecture
x86_64, ARM64 (Apple Silicon & Graviton)
🧠 How It Works
FastFlowLM coordinates its core functionality through a modular C++ pipeline. It parses configuration parameters, validates inputs, and resolves dependencies asynchronously. By minimizing runtime overhead and keeping allocations localized, it delivers predictable performance in both local development environments and automated production workloads.
🎯 Production Use Cases
Autonomous AI Agents
Orchestrate intelligent workflows and tool-calling routines with FastFlowLM.
Model Inference & Prompting
Integrate fast, local or cloud-hosted generative AI models directly into production code.
Context Memory & RAG
Augment language models with dynamic vector retrieval and structured project memory.
Developer Productivity
Automate repetitive engineering tasks, code generation, and test creation using AI agents.
🚀 Getting Started
Install FastFlowLM using your package manager: `git clone https://github.com/ROCm/FastFlowLM.git`
Initialize your project workspace or configuration file for FastFlowLM.
Import FastFlowLM into your codebase or invoke it directly from your terminal.
Execute your test suite or run `FastFlowLM --help` to verify successful setup.
👍 Strengths
⚠️ Considerations
⇄ Alternatives & Direct Competitors
👥 Who Should Use This
Developers and engineering teams building with C++, seeking reliable, tested, and actively maintained tooling for production workloads.
🏆 Nearby in the Rankings
ROCm/FastFlowLM is currently ranked #1,938 by stars across every repository tracked on GitHubRepo. These are adjacent projects:
| Rank | Repository | Language | Stars | Action |
|---|---|---|---|---|
| #1,933 | selenide/selenide | Java | ★ 1.9K | Compare ↗ |
| #1,933 | gocardless/statesman | Ruby | ★ 1.9K | Compare ↗ |
| #1,933 | ZalithLauncher/ZalithLauncher2 | Kotlin | ★ 1.9K | Compare ↗ |
| #1,936 | FGRibreau/mailchecker | PHP | ★ 1.9K | Compare ↗ |
| #1,936 | featbit/featbit | C# | ★ 1.9K | Compare ↗ |
| #1,938 | ROCm/FastFlowLM This Project | C++ | ★ 1.9K | |
| #1,938 | lineofflight/frankfurter | Ruby | ★ 1.9K | Compare ↗ |
| #1,940 | mikependon/RepoDB | C# | ★ 1.9K | Compare ↗ |
| #1,941 | rakudo/rakudo | Raku | ★ 1.9K | Compare ↗ |
| #1,941 | didriksg/Crisp | Swift | ★ 1.9K | Compare ↗ |
| #1,943 | evoluhq/evolu | TypeScript | ★ 1.9K | Compare ↗ |
Frequently Asked Questions
What does FastFlowLM do? +
Run LLMs on AMD Ryzen™ AI NPUs in minutes; purpose-built and deeply optimized for the AMD NPUs.
What language is FastFlowLM written in? +
The primary language is C++. Topics include: amd, deepseek, llama, llm, npu.
Is FastFlowLM actively maintained? +
Yes, the last recorded push was on Sep 24, 2026 with 182 open issues being tracked.
How many stars does FastFlowLM have? +
FastFlowLM has 1,905 stars and 155 forks on GitHub.
How does FastFlowLM rank among GitHub repositories? +
With 1,905 stars, ROCm/FastFlowLM is ranked #1,938 globally across all repositories tracked on GitHubRepo and #138 among C++ projects.
What license is FastFlowLM distributed under? +
The repository reports a MIT license. Always verify the repository LICENSE file for legal terms.
