From 0c3fcc46190e3f5dd9a5be805989418b0d280483 Mon Sep 17 00:00:00 2001 From: Nicklas Hansen Date: Sun, 10 Nov 2024 12:32:57 -0800 Subject: [PATCH] update readme --- README.md | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 0e74c2f..441ddd6 100755 --- a/README.md +++ b/README.md @@ -12,11 +12,9 @@ Official implementation of ---- -**Note: the `speedups` branch is experimental and may contain bugs. Please use the `main` branch for the latest stable release.** +**Announcement: training just got ~4.5x faster!** -Expect **3-8x** faster wall-time (depending on hardware and task) compared to `main` branch. A majority of the speedups in this branch are enabled with the additional flag `compile=true`. To run the code with `compile=true`, **you will need to install the latest `nightly` versions of PyTorch, TensorDict, and TorchRL**. See `docker/environment.yaml` for a tested configuration. We are not responsible for any issues that may arise from using our repository. - -Thank you to [Vincent Moens](https://github.com/vmoens) who has been a key contributor to this branch! +Expect **~4.5x** faster wall-time (depending on hardware and task) with the most recent release (Nov 10, 2024). A majority of the speedups in this branch are enabled with the additional flag `compile=true`. To run the code with `compile=true`, **you will need to install the latest `nightly` versions of PyTorch, TensorDict, and TorchRL**. See `docker/environment.yaml` for a tested configuration. `compile=true` is available in state-based online RL at the moment, and we expect to roll out support across all settings in the coming months. Thank you to [Vincent Moens](https://github.com/vmoens) who has been a key contributor to our torch.compile compatibility! ----