docs: replace Ollama comparisons with product-first framing

Describe the CLI on its own terms ("familiar single-command CLI") instead
of positioning FLM relative to Ollama.

Functional references are unchanged: setup steps that name Ollama UI
controls, the langchain_ollama examples, code identifiers, and the
llama.cpp/Ollama acknowledgements all still apply.

Co-Authored-By: Claude <noreply@anthropic.com>

Author: tawei-amd

README.md

@@ -14,7 +14,7 @@ Run large language models — now with **Vision**, **Audio**, **Embedding** and
 **No GPU required. Faster and over 10× more power-efficient. Supports context lengths up to 256k tokens. Ultra-Lightweight (17 MB). Installs within 20 seconds.**
 
 📦 **The only out-of-box, NPU-first runtime built exclusively for Ryzen™ AI.**  
-🤝 **Think Ollama — but deeply optimized for NPUs.**  
+🤝 **A familiar single-command CLI — deeply optimized for NPUs.**  
 ✨ **From Idle Silicon to Instant Power — FastFlowLM Makes Ryzen™ AI Shine.**
 
 > FastFlowLM (FLM) supports all Ryzen™ AI Series chips with XDNA2 NPUs (Strix, Strix Halo, Kraken, and Gorgon Point).
@@ -107,7 +107,7 @@ No model rewrites, no tuning — it just works.
 
 - **Runs fully on AMD Ryzen™ AI NPU** — no GPU or CPU load
 - **Lightweight runtime (17 MB)** — installs within **20 seconds**, easy to integrate    
-- **Developer-first flow** — like Ollama, but optimized for NPU  
+- **Developer-first flow** — a familiar single-command CLI, optimized for NPU  
 - **Support for long context windows** — up to 256k tokens (e.g., Qwen3-4B-Thinking-2507)  
 - **No low-level tuning required** — You focus on your app, we handle the rest
 

docs/_includes/hero-home.html

@@ -6,7 +6,7 @@ <h1 class="headline-xl">
         Run frontier LLMs directly on Ryzen™ AI NPUs
       </h1>
       <p class="copy-lg">
-        FastFlowLM delivers an Ollama-style developer experience that is tuned for AMD’s XDNA2 accelerators:
+        FastFlowLM delivers a familiar single-command developer experience that is tuned for AMD’s XDNA2 accelerators:
         install in seconds, stream tokens instantly, and sustain up to 256k context windows with 10× better
         efficiency than GPU-first stacks.
       </p>

docs/docs/index.md

@@ -11,7 +11,7 @@ has_children: false
 
 Run **LLMs — now with Vision support — in minutes**: **no GPU required**, **over 10× more power-efficient**, and with **context lengths up to 256k tokens**.  
 
-Think **Ollama — but laser-optimized for NPUs**.  
+A **familiar single-command CLI — laser-optimized for NPUs**.  
 
 From *idle silicon* to *instant power* — **FastFlowLM makes Ryzen™ AI shine.**
 

docs/docs/instructions/cli.md

@@ -7,7 +7,7 @@ parent: Instructions
 
 # ⚡ CLI Mode
 
-FLM CLI mode offers a terminal-based interactive experience, similar to Ollama, but fully offline and accelerated exclusively on AMD NPUs. Here are detailed descriptions of commands and setup for CLI mode usage. It includes:
+FLM CLI mode offers a familiar terminal-based interactive experience, fully offline and accelerated exclusively on AMD NPUs. Here are detailed descriptions of commands and setup for CLI mode usage. It includes:
 
 - **[🔧 Pre-Run PowerShell Commands (System)](#-pre-run-powershell-commands)**
 - **[💻 Commands Inside CLI Mode](#-commands-inside-cli-mode)**

docs/docs/instructions/index.md

@@ -10,7 +10,7 @@ has_children: true
 **FastFlowLM (FLM)** is a deeply optimized runtime for **local LLM inference on AMD NPUs** —  
 ultra-fast, power-efficient, and 100% offline.
 
-Its user interface and workflow are similar to **Ollama**, but purpose-built for AMD's XDNA architecture.
+Its user interface and workflow follow a **familiar single-command CLI**, purpose-built for AMD's XDNA architecture.
 
 This section will walk you through how to use FastFlowLM with examples.
 

docs/index.md

@@ -2,14 +2,14 @@
 layout: page
 title: "FastFlowLM"
 permalink: /
-description: "Ollama-style runtime that unlocks AMD Ryzen AI NPUs with instant installs, rich models, and matching docs."
+description: "NPU-native runtime that unlocks AMD Ryzen AI NPUs with instant installs, rich models, and matching docs."
 sections:
   - type: hero
     id: top
     kicker: "NPU-first runtime"
     title: "The fastest, most efficient LLM inference on NPUs"
     body: |
-      FastFlowLM (FLM) delivers an Ollama-style developer experience built exclusively for AMD Ryzen™ AI NPUs. Install in seconds, stream tokens instantly, and run context windows up to 256k — all with dramatically better efficiency than GPU-first stacks.
+      FastFlowLM (FLM) delivers a familiar single-command developer experience built exclusively for AMD Ryzen™ AI NPUs. Install in seconds, stream tokens instantly, and run context windows up to 256k — all with dramatically better efficiency than GPU-first stacks.
       
       The FastFlowLM team is now part of AMD.
     ctas:
@@ -54,7 +54,7 @@ sections:
                 - "Over 10× power efficiency"
                 - "256k ctx"
                 - "Vision · Audio · OMNI · Text"
-          - title: "Ollama‑Style Developer Flow"
+          - title: "Familiar Developer Flow"
             description: "Same simple CLI & API patterns you already know — deeply optimized for NPU performance."
             visual:
               type: "code"
@@ -152,7 +152,7 @@ sections:
       kicker: "Install"
       title: "From download to first token in under a minute"
       body: |
-        FastFlowLM ships as a 17 MB runtime with an Ollama-style CLI and a server compatible with the OpenAI API.
+        FastFlowLM ships as a 17 MB runtime with a familiar single-command CLI and a server compatible with the OpenAI API.
         No drivers, no guesswork—just run the installer, pull a model, and start chatting.
       items:
         - heading: "Zero-conf installer"