-
### 🐛 Describe the bug
I am hosting a bert-like model using below torchserve config.
```
inference_address=http://localhost:8080
management_address=http://localhost:8081
metrics_address=http://lo…
-
**Describe the feature**
Support to deploy to torchserve
**Motivation**
Maybe the most straightforward way for me to deploy mmrotate
**Related resources**
https://github.com/open-mmlab/mmdete…
-
Hello,
I was trying to setup local run on my mac and got this error when running: "torchserve --start --ts-config config.local.properties --foreground" And got a no module named "nvgpu" error.
…
-
Im trying to deploy my setfit model in torchserver using a custom handler for this task. The thing is that im not being able to do this since im getting multiple errors while registering the model on …
-
- 현재 TorchServe handler를 init할 때 확장성이 너무 떨어지는 것 같음.
- 확장성, 재사용성이 높은 코드를 짤 필요가 있다.
- 현재 하드코딩되어 있는 부분들이 너무 많다.
- 여러 모델들을 추가하는 것을 가정하고 짜자.
```Python
def initialize(self, ctx):
self.mani…
-
Hi Tsunami Team,
I'd like to contribute a plugin for "RCE in TorchServe Management API".
The plugin detects an exposed TorchServe Management API service and verifies code execution through a malic…
-
Can I set the init status of Torchserve as start?
-
(chat0.3_py310) ubuntu@ubuntu-virtual-machine:~/wy_pj/chat-tts-ui$ sudo docker compose -f docker-compose.cpu.yaml up -d --build
WARN[0000] The "UID" variable is not set. Defaulting to a blank string.…
-
The closest example that I could find is https://github.com/pytorch/serve/tree/issue_390/examples/semantic_search. However, this seems a bit ad-hoc and also the model files seem to be different now. I…
-
/kind bug
**What steps did you take and what happened:**
I've created an InferenceService from PyTorch model with torchserve-kfs runtime version 0.7.0 (see .yaml file below). Then I've made a re…