Comments (2)
Hi @IonBoleac,
the difference is that for module level entry point you provide a single function that is called for model initialization and prediction (handle). It is supposed to take two arguments: data and ctx. If data is None the function should initialize the model. When data is not None do inference on it. In the class level entry point case this corresponds to the two methods that need to be provided by the class: initialize and handle. The recommended way (and the one most if not all our examples use) is the class level entry point where you start by deriving from BaseHandler and implement initialize. The handle method is already implemented by BaseHandler and you only need to overwrite pre-/postprocessing and inference depending on your use case.
Hope that helps. Let me know if you still have questions. Happy to dive deeper into this.
Matthias
from serve.
Closing this issue for now. Feel free to re-open if you have further questions.
from serve.
Related Issues (20)
- Serve multiple models with both CPU and GPU HOT 3
- How to modify torchserve’s Python runtime from 3.8.0 to 3.10 HOT 1
- TorchServe crashes in production with `WorkerThread - IllegalStateException error' HOT 4
- Unable to use build_image.sh to build the cu102 version of the image HOT 2
- Metrics collector crashes when NVIDIA MIGs are present HOT 1
- Server crashes in production with `WorkerThread - IllegalStateException error' HOT 1
- Whether the pre- and post-processing operations of batch processing are parallel HOT 1
- Update cpp/llamacpp to Llama 3 HOT 1
- Update LLM/llama2 to Llama3
- Update large_models/inferentia2/llama2 to Llama3
- Update large_models/tp_llama to llama3
- Update large_models/gpt_fast to llama3
- How to pass parameters from preprocessing to postprocessing when using micro-batch operations HOT 4
- Load model failed - error: Worker died HOT 6
- Docker regression failure: test_handler_traceback_logging.py
- Exchange Llama2 against Llama3 in HF_accelerate example
- CUDA out of Memory with low Memory Utilization (CUDA error: device-side assert triggered) HOT 5
- If micro_batch_size of micro-batch is set to 1, then model inference is still batch processing? HOT 1
- question to model inference optimization HOT 1
- Duplicate base_neuronx_continuous_batching_handler.py 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.