From b5dcb446c3773802252980e2ec01abeabae25dc3 Mon Sep 17 00:00:00 2001
From: zaneni6
efficiency than GPU-first stacks.
Invoke-WebRequest https://github.com/FastFlowLM/FastFlowLM/releases/latest/download/flm-setup.exe `
+ Invoke-WebRequest https://github.com/ROCm/FastFlowLM/releases/latest/download/flm-setup.exe `
-OutFile flm-setup.exe
Start-Process .\flm-setup.exe -Wait
diff --git a/docs/docs.md b/docs/docs.md
index 27f7ea02..4bb80167 100644
--- a/docs/docs.md
+++ b/docs/docs.md
@@ -57,7 +57,7 @@ sections:
Liquid shortcodes + markdown tables keep everything portable.
ctas:
- label: "Edit on GitHub"
- href: "https://github.com/FastFlowLM/FastFlowLM/tree/main/docs"
+ href: "https://github.com/ROCm/FastFlowLM/tree/main/docs"
style: ghost
external: true
right:
diff --git a/docs/docs/install_lin.md b/docs/docs/install_lin.md
index f58fcd52..3f4e36ba 100644
--- a/docs/docs/install_lin.md
+++ b/docs/docs/install_lin.md
@@ -15,7 +15,7 @@ Get set up and then show us what you build!
## π’ FastFlowLM Linux Support
-[FastFlowLM](https://github.com/FastFlowLM/FastFlowLM) is a lightweight LLM runtime optimized for **AMD NPUs**.
+[FastFlowLM](https://github.com/ROCm/FastFlowLM) is a lightweight LLM runtime optimized for **AMD NPUs**.
Today, FastFlowLM is adding support for **Ubuntu, Arch, and other distros** to enable **fast, low-power LLMs** on **Ryzenβ’ AI PCs that run Linux**.
This article will help you:
@@ -102,7 +102,7 @@ sudo reboot
```
#### 4. Install FastFlowLM
-- Download the latest `.deb` package from the [Releases page](https://github.com/FastFlowLM/FastFlowLM/releases):
+- Download the latest `.deb` package from the [Releases page](https://github.com/ROCm/FastFlowLM/releases):
```sh
sudo apt install ./fastflowlm*.deb
@@ -168,7 +168,7 @@ If `flm validate` passes but `flm run` fails with `No such device with index '0'
1. Clone the repository:
```sh
- git clone https://github.com/FastFlowLM/FastFlowLM.git
+ git clone https://github.com/ROCm/FastFlowLM.git
cd FastFlowLM
```
2. Build:
diff --git a/docs/docs/install_win.md b/docs/docs/install_win.md
index c9331c61..06af47ac 100644
--- a/docs/docs/install_win.md
+++ b/docs/docs/install_win.md
@@ -32,7 +32,7 @@ You must have AMD NPU driver **version number >= 32.0.203.304** (`.304` is the m
## πΎ Install FastFlowLM (Windows)
A packaged FLM Windows installer is available here:
-[**flm-setup.exe**](https://github.com/FastFlowLM/FastFlowLM/releases/latest/download/flm-setup.exe)
+[**flm-setup.exe**](https://github.com/ROCm/FastFlowLM/releases/latest/download/flm-setup.exe)
> To install silently, open PowerShell, navigate (`cd`) to the download folder, and run:
@@ -46,7 +46,7 @@ If you see **"Windows protected your PC"**, click **More info**, then select **R
πΊ [**Watch the quick start video**](https://www.youtube.com/watch?v=mYOfDNkyBII)
-For version history and changelog, see the [release notes](https://github.com/FastFlowLM/FastFlowLM/releases/).
+For version history and changelog, see the [release notes](https://github.com/ROCm/FastFlowLM/releases/).
---
diff --git a/docs/docs/instructions/cli.md b/docs/docs/instructions/cli.md
index 2cc1dd12..bea46999 100644
--- a/docs/docs/instructions/cli.md
+++ b/docs/docs/instructions/cli.md
@@ -470,7 +470,7 @@ Example:
* **No quotes** around the prompt
* File must be plain text (readable in Notepad)
-π [Download a sample prompt (around 40k tokens)](https://github.com/FastFlowLM/FastFlowLM/blob/main/assets/alice_in_wonderland.txt)
+π [Download a sample prompt (around 40k tokens)](https://github.com/ROCm/FastFlowLM/blob/main/assets/alice_in_wonderland.txt)
> β οΈ **Caution:** a modelβs supported context length is limited by available DRAM capacity. For example, with **32 GB** of DRAM, **LLaMA 3.1:8B** cannot run beyond a **32K** context length. For the full **128K** context, we recommend larger memory system.
diff --git a/docs/docs/instructions/server/openapi.md b/docs/docs/instructions/server/openapi.md
index f9b109f2..8b68f4f4 100644
--- a/docs/docs/instructions/server/openapi.md
+++ b/docs/docs/instructions/server/openapi.md
@@ -210,7 +210,7 @@ gc.collect()
You can load a full `.txt` file as a prompt β useful for long documents or testing large context windows.
-π [Download the sample prompt](https://github.com/FastFlowLM/FastFlowLM/blob/main/assets/alice_in_wonderland.txt)
+π [Download the sample prompt](https://github.com/ROCm/FastFlowLM/blob/main/assets/alice_in_wonderland.txt)
Download to Downloads folder. This contains over 38k token, thus may take longer to prompt. FastFlowLM supports full context length (32kβ128k), making it ideal for processing long documents like this
diff --git a/docs/docs/instructions/server/rag_LangChain.md b/docs/docs/instructions/server/rag_LangChain.md
index ecd41d56..1808b59e 100644
--- a/docs/docs/instructions/server/rag_LangChain.md
+++ b/docs/docs/instructions/server/rag_LangChain.md
@@ -30,7 +30,7 @@ This guide walks you through building a **Retrieval-Augmented Generation (RAG)**
### β
Install FastFlowLM (local server)
Download from GitHub Releases:
-π https://github.com/FastFlowLM/FastFlowLM
+π https://github.com/ROCm/FastFlowLM
Launch the server:
diff --git a/docs/docs/instructions/server/websearch_LangChain.md b/docs/docs/instructions/server/websearch_LangChain.md
index 2c20b5c9..7a30e8eb 100644
--- a/docs/docs/instructions/server/websearch_LangChain.md
+++ b/docs/docs/instructions/server/websearch_LangChain.md
@@ -18,7 +18,7 @@ This project demonstrates how to build a lightweight Retrieval-Augmented Generat
- Windows machine
- Python 3.9 or later
-- [FastFlowLM](https://github.com/FastFlowLM/FastFlowLM) installed
+- [FastFlowLM](https://github.com/ROCm/FastFlowLM) installed
- FastFlowLM model served (e.g., `llama3.2:1b`)
---
diff --git a/docs/index.md b/docs/index.md
index faa83a90..f2f84592 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -14,11 +14,11 @@ sections:
The FastFlowLM team is now part of AMD.
ctas:
- label: "Download FastFlowLM (Windows)"
- href: "https://github.com/FastFlowLM/FastFlowLM/releases/latest/download/flm-setup.exe"
+ href: "https://github.com/ROCm/FastFlowLM/releases/latest/download/flm-setup.exe"
style: primary
external: true
- label: "GitHub"
- href: "https://github.com/FastFlowLM/FastFlowLM"
+ href: "https://github.com/ROCm/FastFlowLM"
style: ghost
external: true
- label: "Models"
@@ -166,7 +166,7 @@ sections:
code_blocks:
- title: "CLI"
content: |
- Invoke-WebRequest https://github.com/FastFlowLM/FastFlowLM/releases/latest/download/flm-setup.exe `
+ Invoke-WebRequest https://github.com/ROCm/FastFlowLM/releases/latest/download/flm-setup.exe `
-OutFile flm-setup.exe
Start-Process .\flm-setup.exe -Wait
flm pull llama3.2:3b
diff --git a/docs/linux-getting-started.md b/docs/linux-getting-started.md
index 65e0b0a4..8b65a74d 100644
--- a/docs/linux-getting-started.md
+++ b/docs/linux-getting-started.md
@@ -42,7 +42,7 @@ sudo reboot
```
#### 4. Install FastFlowLM
-- Download the latest `.deb` package from the [Releases page](https://github.com/FastFlowLM/FastFlowLM/releases):
+- Download the latest `.deb` package from the [Releases page](https://github.com/ROCm/FastFlowLM/releases):
```sh
sudo apt install ./fastflowlm*.deb
@@ -127,7 +127,7 @@ In short: if 1.1 firmware breaks probing on stock 6.19, do not keep forcing the
2. Clone the repository and pull all submodules:
```sh
- git clone --recursive https://github.com/FastFlowLM/FastFlowLM.git
+ git clone --recursive https://github.com/ROCm/FastFlowLM.git
cd FastFlowLM
```
3. Build:
diff --git a/docs/models.md b/docs/models.md
index 46b1a53f..a8ff0cc5 100644
--- a/docs/models.md
+++ b/docs/models.md
@@ -50,7 +50,7 @@ sections:
title: "Stay in the loop"
ctas:
- label: "Release notes"
- href: "https://github.com/FastFlowLM/FastFlowLM/releases"
+ href: "https://github.com/ROCm/FastFlowLM/releases"
style: primary
external: true
- label: "Discord"
diff --git a/docs/news.md b/docs/news.md
index c72e8e29..c176406a 100644
--- a/docs/news.md
+++ b/docs/news.md
@@ -11,7 +11,7 @@ sections:
Stay up to date with FastFlowLM releases, community highlights, and technical deep dives.
ctas:
- label: "GitHub Releases"
- href: "https://github.com/FastFlowLM/FastFlowLM/releases"
+ href: "https://github.com/ROCm/FastFlowLM/releases"
style: primary
external: true
- label: "Join Discord"
diff --git a/docs/team.md b/docs/team.md
index bdffe037..54349122 100644
--- a/docs/team.md
+++ b/docs/team.md
@@ -85,7 +85,7 @@ sections:
href: "mailto:info@fastflowlm.com"
style: primary
- label: "Open an issue"
- href: "https://github.com/FastFlowLM/FastFlowLM/issues/new"
+ href: "https://github.com/ROCm/FastFlowLM/issues/new"
style: ghost
external: true
---