Comments (2)
Hi, if you are still interested in this, we have made some changes to the batching recently.
Now the batch might be split into smaller pieces to fit the max batch size.
For example, if the max_batch_size is 10 and we send 3 requests with size of [7, 7, 6] in receiving order, the batch engine will execute with size of 7+3 and 4+6 sequentially, the second request is split in to two parts with size of (3, 4).
from bentoml.
@frostming
Thanks for keeping me updated :)
If I understand correctly your comment applies to when the client sends data in batches. In that case, the batches are now rebuilt to better fit the max batch size argument.
This is not the feature I wish existed. I would really like it if we had more options to customize the way batches are made, like for instance only batching together inputs that share a same metadata field. This is key to getting the best performance in some cases, like the example in my original post.
Maybe it is already possible to do something by subclassing the class that handles batching ? It is not mentionned in the documentation.
from bentoml.
Related Issues (20)
- Bug: 'bentoml containerize' doesn't include models in the image
- bug: Cannot use pydantic models with namedtuples
- bug: SSL does not work HOT 2
- bug: bentoml.transformers.save_model doesn't work with WhisperFeatureExtractor
- minor bug: Swagger docs.json not correctly specified for list[PydanticModel] Output
- bug: pydantic/pathlib patching causes `LookupError: <ContextVar name='request_directory' at 0x172a18860>` HOT 1
- bug: ModuleNotFoundError: No module named 'bentoml.frameworks'
- bug: Cannot specify Numpy DType and Shape with Pydantic as deletion contains a bug.
- bug: Cannot install Development environment using pdm HOT 2
- feature: support bentoml.depends.from_url("http://already.deployed-bento.com:3000")
- bug: memory leak when I am using bentoml>=1.2 HOT 28
- feature: Use tcmalloc in supported platform as default memory allocator
- bug: Cannot get logging to work with monitoring resource
- bug: Excessive time spent parsing pydantic version
- bug: timeout configuration not work HOT 1
- feature: serialization/deserialization with `ormsgpack`
- bug: a lot of missing testing for the `_bento_sdk` package
- bug: Generic exceptions from HTTP client
- feature: To be able to define custom metrics endpoint
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 bentoml.