include bp link.

Author: sayakpaul

docs/source/en/optimization/fp16.md

@@ -239,6 +239,13 @@ The `step()` function is [called](https://github.com/huggingface/diffusers/blob/
 
 In general, the `sigmas` should [stay on the CPU](https://github.com/huggingface/diffusers/blob/35a969d297cba69110d175ee79c59312b9f49e1e/src/diffusers/schedulers/scheduling_euler_discrete.py#L240) to avoid the communication sync and latency.
 
+<Tip>
+
+Refer to [this blog post](https://pytorch.org/blog/torch-compile-and-diffusers-a-hands-on-guide-to-peak-performance/) for a comprehensive coverage on how to use
+`torch.compile` for getting maximum performance in Diffusers for various scenarios. 
+
+</Tip>
+
 ### Benchmarks
 
 Refer to the [diffusers/benchmarks](https://huggingface.co/datasets/diffusers/benchmarks) dataset to see inference latency and memory usage data for compiled pipelines.