lxning

**Link to the notebook** Add the link to the notebook. https://github.com/aws/amazon-sagemaker-examples/blob/main/sagemaker-python-sdk/pytorch_batch_inference/sagemaker_batch_inference_torchserve.ipynb **Describe the bug** A clear and concise description of what the bug is. Run the notebook, i found the...

deprecate ci benchmark dir

1

## Description Please read our [CONTRIBUTING.md](https://github.com/pytorch/serve/blob/master/CONTRIBUTING.md) prior to creating your first pull request. Please include a summary of the feature or issue being fixed. Please also include relevant motivation and...

[RFC]: Metrics Refactoring

12

### Current TorchServe has two mechanisms to emit metrics. 1. [Emit metrics to logs files in a StatsD like format by default](https://github.com/pytorch/serve/blob/master/docs/metrics.md#formatting) . In this case, both frontend and backend...

upgrade PT to 1.12

3

## Description Please read our [CONTRIBUTING.md](https://github.com/pytorch/serve/blob/master/CONTRIBUTING.md) prior to creating your first pull request. Please include a summary of the feature or issue being fixed. Please also include relevant motivation and...

### 🚀 The feature upgrade to PT1.12 ### Motivation, pitch PT 1.12 was released. TS needs to upgrade to PT1.12 ### Alternatives _No response_ ### Additional context _No response_

## Description Please read our [CONTRIBUTING.md](https://github.com/pytorch/serve/blob/master/CONTRIBUTING.md) prior to creating your first pull request. Please include a summary of the feature or issue being fixed. Please also include relevant motivation and...

### 🚀 The feature According to [PyTorch installation instruction](https://pytorch.org/), Torchserve needs to update PyTorch installation and docker for Mac M1. "MacOS Conda binaries are for x86_64 only, for M1 please...

DLRM example

1

please provide [DLRM](https://github.com/facebookresearch/dlrm) example. ## Is your feature request related to a problem? Please describe. ## Describe the solution ## Describe alternatives solution

This is java frontend work in cpp backend milestone1. ## Is your feature request related to a problem? Please describe. ## Describe the solution ## Describe alternatives solution

add OMP_NUM_THREADS default as 1 for CPU device in config.properties

1

## Is your feature request related to a problem? Please describe. According to [known issue](https://github.com/pytorch/pytorch/issues/3146), it can optimize performance for CPU to set "OMP_NUM_THREADS". So it is convenient for users...