Clarify GPU chat inference instructions

microsoft · Feb 14, 2025 · 80334f5 · 80334f5
1 parent 818fc64
commit 80334f5
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/docs/genai/tutorials/deepseek-python.md b/docs/genai/tutorials/deepseek-python.md
@@ -51,6 +51,6 @@ python model-chat.py -m deepseek-r1-distill-qwen-1.5B/model -e cpu --chat_templa
 ```
 
 ```bash
-# GPU Chat inference. If you pulled the model from huggingface, adjust the model directory (-m) accordingly 
+# On-Device GPU Chat inference. Works on devices with Nvidia GPUs. If you pulled the model from huggingface, adjust the model directory (-m) accordingly 
 curl -o https://raw.githubusercontent.com/microsoft/onnxruntime-genai/refs/heads/main/examples/python/model-chat.py
 python model-chat.py -m deepseek-r1-distill-qwen-1.5B/model -e cuda --chat_template "<|begin▁of▁sentence|><|User|>{input}<|Assistant|>"