Update README.md

README.md

@@ -31,6 +31,9 @@ It achieves the following results on the evaluation set:
 
 ## usage 
 
+> [!TIP]
+> BART supports several speedups for inference on GPU, including [flash-attention2](https://huggingface.co/docs/transformers/perf_infer_gpu_one#flashattention-2) and [torch SDPA](https://huggingface.co/docs/transformers/perf_infer_gpu_one#pytorch-scaled-dot-product-attention)
+
 an example of aggregating summaries from chunks of a long document:
 
 ```py
@@ -66,6 +69,7 @@ res = pipe(
 print(res[0]["generated_text"])
 ```
 
+
 ## Training procedure
 
 ### Training hyperparameters