Comments (3)
A report from the quick run of benchmarks on select models.
TorchServeBenchmarkingResults.pdf
What's Useful:
- Gauge the Inference Times, Client Round Trip Times.
- Stability of Server over sustained Client requests, internal tests show this sustains for much longer.
- Worst Case Latency expected.
What's missing are:
- Needs running on GPU instances
- More models to be covered
- Separation of Inference Time and Overhead from TorchServe
from serve.
@mycpuorg For Throughput Benchmarking you can use: https://github.com/pytorch/pytorch/blob/master/torch/utils/throughput_benchmark.py#L62
Please ensure to have some warmup threads prior to collecting the actual stats.
from serve.
Closing this as we now have an apache-bench based benchmarking script which is used for benchmarking TorchServe against different PyTorch models.
from serve.
Related Issues (20)
- 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
- Clean up metrics documentation
- How to 'Create model archive pod and run model archive file generation script' in the ‘User Guide’ HOT 3
- [RFC]: Deprecation notice for TorchServe macOS x86 builds, binaries & testing
- very high QueueTime
- Add support for MPS in the basehandler HOT 1
- torchserve output customization HOT 3
- Exception when using torchserve to deploy hugging face model: java.lang.InterruptedException: null HOT 4
- Real-time Object Detection HOT 4
- PyTorch Serve: Custom handler not saving inference results HOT 6
- PyTorch serve with custom translators returning Unknown exception HOT 4
- Newer Base Image KServe Container fails with exec /usr/local/bin/dockerd-entrypoint.sh: exec format error HOT 7
- Reduce or remove worker retries for specific failures HOT 6
- Update describe model management API to show all model configuration options
- support install cpp dependency in auto-benchmark
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.