Skip to content

Commit 33bdf65

Browse files
nv-kkudrynskinv-kkudrynski
committed
readme fixes
1 parent 7f4ea44 commit 33bdf65

3 files changed

Lines changed: 0 additions & 6 deletions

File tree

‎PyTorch/Detection/SSD/README.md‎

Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -216,8 +216,6 @@ To enable mixed precision, you can:
216216
217217
#### Enabling TF32
218218
219-
This section is model specific and needs to show how to enable TF32. How is TF32 being implemented? Tweaking layers, preprocessing data, etc…
220-
221219
TensorFloat-32 (TF32) is the new math mode in [NVIDIA A100](#https://www.nvidia.com/en-us/data-center/a100/) GPUs for handling the matrix math also called tensor operations. TF32 running on Tensor Cores in A100 GPUs can provide up to 10x speedups compared to single-precision floating-point math (FP32) on Volta GPUs.
222220
223221
TF32 Tensor Cores can speed up networks using FP32, typically with no loss of accuracy. It is more robust than FP16 for models which require high dynamic range for weights or activations.

‎TensorFlow/Detection/SSD/README.md‎

Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -160,8 +160,6 @@ To enable mixed precision, you can simply add the values to the environmental va
160160

161161
#### Enabling TF32
162162

163-
This section is model specific and needs to show how to enable TF32. How is TF32 being implemented? Tweaking layers, preprocessing data, etc…
164-
165163
TensorFloat-32 (TF32) is the new math mode in [NVIDIA A100](https://www.nvidia.com/en-us/data-center/a100/) GPUs for handling the matrix math also called tensor operations. TF32 running on Tensor Cores in A100 GPUs can provide up to 10x speedups compared to single-precision floating-point math (FP32) on Volta GPUs.
166164

167165
TF32 Tensor Cores can speed up networks using FP32, typically with no loss of accuracy. It is more robust than FP16 for models which require high dynamic range for weights or activations.

‎TensorFlow/LanguageModeling/Transformer-XL/README.md‎

Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -280,8 +280,6 @@ To enable mixed precision, you can simply add the values to the environmental va
280280

281281
#### Enabling TF32
282282

283-
This section is model specific and needs to show how to enable TF32. How is TF32 being implemented? Tweaking layers, preprocessing data, etc…
284-
285283
TensorFloat-32 (TF32) is the new math mode in [NVIDIA A100](https://www.nvidia.com/en-us/data-center/a100/) GPUs for handling the matrix math also called tensor operations. TF32 running on Tensor Cores in A100 GPUs can provide up to 10x speedups compared to single-precision floating-point math (FP32) on Volta GPUs.
286284

287285
TF32 Tensor Cores can speed up networks using FP32, typically with no loss of accuracy. It is more robust than FP16 for models which require high dynamic range for weights or activations.

0 commit comments

Comments
 (0)