Make the hardware wording neutral

README.md

@@ -8,7 +8,6 @@ tags:
 - classification
 - qwen3_5
 - pytorch
-- rocm
 ---
 
 ![Open Decision Foundation Models — Nox-4B](assets/decision-nox-4b-header.png)
@@ -75,7 +74,7 @@ This downloads the complete model release. The root `config.json` lists the back
 
 ## Serve with vLLM Semantic Router
 
-This repository contains model data only. Use the vLLM Semantic Router Decision runtime to load `llm-semantic-router/Decision-1.0-Nox-4B` and serve Choice, Noul, and Score requests. The serving implementation and its dependencies live in vLLM Semantic Router; this release does not bundle executable model code. `transformers.AutoModel.from_pretrained` cannot load the custom Decision head directly.
+This repository contains model data only. Use the vLLM Semantic Router Decision runtime to load `llm-semantic-router/Decision-1.0-Nox-4B` and serve Choice, Noul, and Score requests. The serving implementation and its dependencies live in vLLM Semantic Router; this release does not bundle executable model code. The weights do not depend on a particular accelerator; which hardware can serve them is decided by the runtime. `transformers.AutoModel.from_pretrained` cannot load the custom Decision head directly.
 
 After configuring a compatible Decision endpoint, send a [SystemOne request](https://docs.typesafe.ai/api) (replace the placeholder URL and key):