Comments (4)
@chauhang : This is by design, as the mar file name on S3 might conflict with the existing mar file in the model_store. The model files from s3 are directly downloaded and extracted in a temp location and loaded into TorchServe.
Also, we are currently working on checkpoint related feature, where the mar files for all the currently registered models, inclusive of the ones downloaded from S3, are backed up by TorchServe in checkpoint's model-store and the models will be directly loaded locally when the checkpoint is restored.
from serve.
@mycpuorg If there is a conflict in the name of the models in the model store and the one being downloaded, it should raise a duplicate name error. Storing models from S3 in yet another temp store is confusing from a Operations point of view. There should be only one model store per deployment to keep things simple for ops.
Let's review this after the Persistent store feature is ready.
from serve.
This has been fixed as part of snapshot feature.
from serve.
PR #171 is merged to master
from serve.
Related Issues (20)
- CPP build failed with errors
- Open Inference Protocol with nightly build not working HOT 6
- CPP backend debugging and troubleshooting
- KServe wrapper default configuration is faulty HOT 5
- Update documentation on deprecating mac x86 support
- It seems like `metrics.yaml` doesn't apply HOT 1
- Config to disable gpu system metrics collection HOT 1
- torch.compile benchmark nightlies failing because of dependency of simpy
- '503 Service Unavailable' for url 'http://0.0.0.0:8085/v1/models/mnist:predict' HOT 2
- Update token authentication doc with maven link for downloading prebuilt plugin HOT 1
- KServe nightly tests are failing
- Incomplete example about emitting metrics HOT 2
- Broken example for a custom Counter metrics HOT 2
- Metrics REST API doesn't return custom metric HOT 3
- Model results are inconsistent between preheating and after preheating HOT 1
- Model with name <name> is not ready. HOT 22
- Improve configuration handling with KServe
- Broken Link to the debug-torchserve-backend page HOT 1
- Setup custom metric with Kubernetes dimensions HOT 1
- Configuration of gRPC MAX_CONNECTION_AGE and MAX_CONNECTION_AGE_GRACE HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from serve.