Fix typo in perf_train_gpu_one.mdx (#17983)

cb425024 · Billy Cao · GitHub · 14fb8a63 · cb425024
Unverified Commit cb425024 authored Jul 01, 2022 by Billy Cao Committed by GitHub Jul 01, 2022
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

docs/source/en/perf_train_gpu_one.mdx docs/source/en/perf_train_gpu_one.mdx +1 -1

No files found.
--- a/docs/source/en/perf_train_gpu_one.mdx
+++ b/docs/source/en/perf_train_gpu_one.mdx
@@ -400,7 +400,7 @@ TrainingArguments(tf32=True)
 ```
 By default the PyTorch default is used.

-Note: tf32 mode is internal to CUDA and can't be accessed directly via `tensor.to(dtype=torch.tf32)` as `torch.tf32` doesn't exit.
+Note: tf32 mode is internal to CUDA and can't be accessed directly via `tensor.to(dtype=torch.tf32)` as `torch.tf32` doesn't exist.

 Note: you need `torch>=1.7` to enjoy this feature.