serve

serve copied to clipboard

has no permission to install library.

1

### 🐛 Describe the bug I'm using the basic docker of pytorch/torchserve:0.6.0-gpu. when I install library in this docker, I met the following errors: Installing collected packages: tifffile, threadpoolctl, scipy,...

jack-gits

When will a new worker be started by Torchserver ?

2

### [Question] As [here](https://pytorch.org/serve/management_api.html#scale-workers) mentioned: > max_worker is the parameter that TorchServe will make no more than this number of workers for the specified model. Does that mean that TorchServe...

NormXU

## 📚 Documentation Related to #1504 Often when new users are debugging their model handler files, they'll make some change then package the model and then inspect logs in `model_log.log`...

msaroufim

Can't serve efficientnet model

7

Hello, I have trained efficientnet model from torchvision and then I tried to serve it with Torchserve but I'm not sure how to implement model.py for the efficientnet_b0 model. I...

MariaBocsa

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

lxning

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...

lxning

Accelerated preprocessing

1

This recent PR by @min-jean-cho https://github.com/pytorch/serve/pull/1545 has made me realize how much performance we're leaving on the table when it comes to acceleration of preprocessing operations. We could more easily...

msaroufim

Do GPU and CPU block each other?

6

## 📚 Documentation Did not find a documentation about processes/threads of GPU and CPU work. During gpu inference can we continue cpu pre/post-processing of other objects asynchronously? If yes, which...

BraginIvan

Replace `install_dependencies.py` by `pip install torchserve[cu111]`

5

Hi, I'm using the package on a computer with a GPU, and the server fails when trying to import [nvgpu](https://github.com/pytorch/serve/blob/e8c8e4934deef4a89cfa5c080480fb8830d5c94b/ts/metrics/system_metrics.py#L61). Any reason why this package is not in the [requirements](https://github.com/pytorch/serve/blob/e8c8e4934deef4a89cfa5c080480fb8830d5c94b/setup.py#L160)...

RobinFrcd

Torchserve 0.4.0 has a dependency on Torch

7

## Context As of `torchserve 0.4.0` there is a dependency on `torch`. I came to realize this when moving from `0.3.1` to `0.4.0`, simply updating the version of `torchserve` in...

lgarciaCoveo