SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Reflect RoCm support in the documentation (#27636)

Browse Source 
* reflect RoCm support in the documentation

* Update docs/source/en/main_classes/trainer.md

Co-authored-by: Lysandre Debut <hi@lysand.re>

* fix review comments

* use ROCm instead of RoCm

---------

Co-authored-by: Lysandre Debut <hi@lysand.re>
This commit is contained in:
fxmarty
2023-11-24 16:59:17 +01:00
committed by GitHub
parent a6d178e238
commit c13a43aaf2
5 changed files with 17 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/source/en/perf_infer_gpu_one.md
View File

@@ -15,7 +15,7 @@ rendered properly in your Markdown viewer.
# GPU inference
GPUs are the standard choice of hardware for machine learning, unlike CPUs, because they are optimized for memory bandwidth and parallelism. To keep up with the larger sizes of modern models or to run these large models on existing and older hardware, there are several optimizations you can use to speed up GPU inference. In this guide, you'll learn how to use FlashAttention-2 (a more memory-efficient attention mechanism), BetterTransformer (a PyTorch native fastpath execution), and bitsandbytes to quantize your model to a lower precision. Finally, learn how to use 🤗 Optimum to accelerate inference with ONNX Runtime on Nvidia GPUs.
GPUs are the standard choice of hardware for machine learning, unlike CPUs, because they are optimized for memory bandwidth and parallelism. To keep up with the larger sizes of modern models or to run these large models on existing and older hardware, there are several optimizations you can use to speed up GPU inference. In this guide, you'll learn how to use FlashAttention-2 (a more memory-efficient attention mechanism), BetterTransformer (a PyTorch native fastpath execution), and bitsandbytes to quantize your model to a lower precision. Finally, learn how to use 🤗 Optimum to accelerate inference with ONNX Runtime on Nvidia and AMD GPUs.
<Tip>
@@ -276,13 +276,13 @@ Feel free to try running a 11 billion parameter [T5 model](https://colab.researc
<Tip>
Learn more details about using ORT with 🤗 Optimum in the [Accelerated inference on NVIDIA GPUs](https://huggingface.co/docs/optimum/onnxruntime/usage_guides/gpu#accelerated-inference-on-nvidia-gpus) guide. This section only provides a brief and simple example.
Learn more details about using ORT with 🤗 Optimum in the [Accelerated inference on NVIDIA GPUs](https://huggingface.co/docs/optimum/onnxruntime/usage_guides/gpu#accelerated-inference-on-nvidia-gpus) and [Accelerated inference on AMD GPUs](https://huggingface.co/docs/optimum/onnxruntime/usage_guides/amdgpu#accelerated-inference-on-amd-gpus) guides. This section only provides a brief and simple example.
</Tip>
ONNX Runtime (ORT) is a model accelerator that supports accelerated inference on Nvidia GPUs. ORT uses optimization techniques like fusing common operations into a single node and constant folding to reduce the number of computations performed and speedup inference. ORT also places the most computationally intensive operations on the GPU and the rest on the CPU to intelligently distribute the workload between the two devices.
ONNX Runtime (ORT) is a model accelerator that supports accelerated inference on Nvidia GPUs, and AMD GPUs that use [ROCm](https://www.amd.com/en/products/software/rocm.html) stack. ORT uses optimization techniques like fusing common operations into a single node and constant folding to reduce the number of computations performed and speedup inference. ORT also places the most computationally intensive operations on the GPU and the rest on the CPU to intelligently distribute the workload between the two devices.
ORT is supported by 🤗 Optimum which can be used in 🤗 Transformers. You'll need to use an [`~optimum.onnxruntime.ORTModel`] for the task you're solving, and specify the `provider` parameter which can be set to either [`CUDAExecutionProvider`](https://huggingface.co/docs/optimum/onnxruntime/usage_guides/gpu#cudaexecutionprovider) or [`TensorrtExecutionProvider`](https://huggingface.co/docs/optimum/onnxruntime/usage_guides/gpu#tensorrtexecutionprovider). If you want to load a model that was not yet exported to ONNX, you can set `export=True` to convert your model on-the-fly to the ONNX format :
ORT is supported by 🤗 Optimum which can be used in 🤗 Transformers. You'll need to use an [`~optimum.onnxruntime.ORTModel`] for the task you're solving, and specify the `provider` parameter which can be set to either [`CUDAExecutionProvider`](https://huggingface.co/docs/optimum/onnxruntime/usage_guides/gpu#cudaexecutionprovider), [`ROCMExecutionProvider`](https://huggingface.co/docs/optimum/onnxruntime/usage_guides/amdgpu) or [`TensorrtExecutionProvider`](https://huggingface.co/docs/optimum/onnxruntime/usage_guides/gpu#tensorrtexecutionprovider). If you want to load a model that was not yet exported to ONNX, you can set `export=True` to convert your model on-the-fly to the ONNX format:
```py
from optimum.onnxruntime import ORTModelForSequenceClassification