maxmustermann/DeepLearningExamples
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

[ConvNets/PyT] update triton repo url in readmes

Browse source
This commit is contained in:
Yuanzhe Dong 2021-07-21 03:53:10 -07:00 committed by GitHub
parent 41e4a07a26
commit 3d8d878489
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
PyTorch/Classification/ConvNets/triton/resnext101-32x4d/README.md
View file

@ -1,6 +1,6 @@
# Deploying the ResNeXt101-32x4d model using Triton Inference Server
The [NVIDIA Triton Inference Server](https://github.com/NVIDIA/trtis-inference-server) provides a datacenter and cloud inferencing solution optimized for NVIDIA GPUs. The server provides an inference service via an HTTP or gRPC endpoint, allowing remote clients to request inferencing for any number of GPU or CPU models being managed by the server.
The [NVIDIA Triton Inference Server](https://github.com/NVIDIA/triton-inference-server) provides a datacenter and cloud inferencing solution optimized for NVIDIA GPUs. The server provides an inference service via an HTTP or gRPC endpoint, allowing remote clients to request inferencing for any number of GPU or CPU models being managed by the server.
This folder contains instructions on how to deploy and run inference on
Triton Inference Server as well as gather detailed performance analysis.
@ -28,7 +28,7 @@ Triton Inference Server as well as gather detailed performance analysis.
The ResNeXt101-32x4d is a model introduced in the [Aggregated Residual Transformations for Deep Neural Networks](https://arxiv.org/pdf/1611.05431.pdf) paper.
It is based on regular ResNet model, substituting 3x3 convolutions inside the bottleneck block for 3x3 grouped convolutions.
The ResNeXt101-32x4d model can be deployed for inference on the [NVIDIA Triton Inference Server](https://github.com/NVIDIA/trtis-inference-server) using
The ResNeXt101-32x4d model can be deployed for inference on the [NVIDIA Triton Inference Server](https://github.com/NVIDIA/triton-inference-server) using
TorchScript, ONNX Runtime or TensorRT as an execution backend.
## Setup

4
PyTorch/Classification/ConvNets/triton/se-resnext101-32x4d/README.md
View file

@ -1,6 +1,6 @@
# Deploying the SE-ResNeXt101-32x4d model using Triton Inference Server
The [NVIDIA Triton Inference Server](https://github.com/NVIDIA/trtis-inference-server) provides a datacenter and cloud inferencing solution optimized for NVIDIA GPUs. The server provides an inference service via an HTTP or gRPC endpoint, allowing remote clients to request inferencing for any number of GPU or CPU models being managed by the server.
The [NVIDIA Triton Inference Server](https://github.com/NVIDIA/triton-inference-server) provides a datacenter and cloud inferencing solution optimized for NVIDIA GPUs. The server provides an inference service via an HTTP or gRPC endpoint, allowing remote clients to request inferencing for any number of GPU or CPU models being managed by the server.
This folder contains instructions on how to deploy and run inference on
Triton Inference Server as well as gather detailed performance analysis.
@ -29,7 +29,7 @@ The SE-ResNeXt101-32x4d is a [ResNeXt101-32x4d](https://arxiv.org/pdf/1611.05431
model with added Squeeze-and-Excitation module introduced
in [Squeeze-and-Excitation Networks](https://arxiv.org/pdf/1709.01507.pdf) paper.
The SE-ResNeXt101-32x4d model can be deployed for inference on the [NVIDIA Triton Inference Server](https://github.com/NVIDIA/trtis-inference-server) using
The SE-ResNeXt101-32x4d model can be deployed for inference on the [NVIDIA Triton Inference Server](https://github.com/NVIDIA/triton-inference-server) using
TorchScript, ONNX Runtime or TensorRT as an execution backend.
## Setup