Highlights
- Arctic Code Vault Contributor
Create your own GitHub profile
Sign up for your own profile on GitHub, the best place to host code, manage projects, and build software alongside 50 million developers.
Sign upPopular repositories
-
-
-
-
Forked from netty/netty
Netty project - an event-driven asynchronous network application framework
Java
-
-
Forked from tensorflow/tensorflow
Computation using data flow graphs for scalable machine learning
C++
941 contributions in the last year
Activity overview
Contribution activity
September 2020
Created a pull request in microsoft/onnxruntime that received 9 comments
Reduce Linux binary size
Description: Strip Linux binary. Will reduce its size by 40%. Motivation and Context Why is this change required? What problem does it solve? If i…
+5
−0
•
9
comments
- [WIP] Enable onnx_test_runner for ort format
- Remove IDeviceAllocator class as it doesn't extend IAllocator
- PipelinesForCuda11Cudnn8
- Fix a few more signed/unsigned warnings in test code.
- Align naming convention and remove redundant code
- Bump bl from 4.0.2 to 4.0.3 in /nodejs
- Add Linux CPU CI for ORT minimal build
- Build docker image instruction fix (CUDA)
- Remove SchedulingParams variants of ThreadPool::TryParallelFor
- Render Operator documentation as compliant markdown
- Imported protoc cannot have compile options.
- Add packages from training docker to cgmanifest.
- Improve performance of CUDA implementations for GatherElements and Greater, Equal and Less
- Fix for initOsArch() always throws when using ORT java on Android
- Pass Model Path to TensorProtoToMLValue from Constant Folding for External Inputs
- Missing header for `std::once_flag` and `std::call_once`.