fixed small typo in code example (#22982)

fixed typo in code example

fixed a really small typo in the docs of single gpu inference

docs/source/en/perf_infer_gpu_one.mdx

@@ -71,7 +71,7 @@ model_name = "bigscience/bloom-2b5"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model_8bit = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", load_in_8bit=True)
 
-text = "Hello, my llama is cute"
+prompt = "Hello, my llama is cute"
 inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
 generated_ids = model.generate(**inputs)
 outputs = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
@@ -105,4 +105,4 @@ Check out the demo for running T5-11b (42GB in fp32)! Using 8-bit quantization o
 
 Or this demo for BLOOM-3B:
 
-[![Open In Colab: BLOOM-3b demo](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1qOjXfQIAULfKvZqwCen8-MoWKGdSatZ4?usp=sharing)
\ No newline at end of file
+[![Open In Colab: BLOOM-3b demo](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1qOjXfQIAULfKvZqwCen8-MoWKGdSatZ4?usp=sharing)