From 8f992e4ca3eb553bddbf8c5e21a6ce4ea4918fd2 Mon Sep 17 00:00:00 2001 From: Sayak Paul Date: Fri, 3 Apr 2026 18:51:36 +0200 Subject: [PATCH] Update README.md --- examples/profiling/README.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/examples/profiling/README.md b/examples/profiling/README.md index dc11e4dec0f9..38b35772d03d 100644 --- a/examples/profiling/README.md +++ b/examples/profiling/README.md @@ -339,4 +339,8 @@ there are still some gaps outside the compiled regions. A full compilation will likely mitigate it. In case it doesn't, the above observations could be useful to mitigate that. * Use of CUDA Graphs can also help mitigate CPU overhead related issues. CUDA Graphs can be enabled by setting the `torch.compile` mode to `"reduce-overhead"` or `"max-autotune"`. -* Diffusers' integration of `torch.compile` is documented [here](https://huggingface.co/docs/diffusers/main/en/optimization/fp16#torchcompile). \ No newline at end of file +* Diffusers' integration of `torch.compile` is documented [here](https://huggingface.co/docs/diffusers/main/en/optimization/fp16#torchcompile). + +## Acknowledgements + +Thanks to [vkuzo](https://github.com/vkuzo) and [jbschlosser](https://github.com/jbschlosser) from the PyTorch team for providing invaluable feedback on the guide.