NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
Role in this project:
ML Engineer Contributions:17 reviews, 12 commits, 31 PRs in 10 months
Contributions summary:Samurdhi primarily contributes to the NVIDIA TensorRT repository, a deep learning inference SDK. Their work focuses on addressing bugs related to TensorFlow integration with TensorRT, specifically resolving hanging issues on Windows when importing TensorFlow after TensorRT. Additionally, the user has added configuration files and enabled attribute tests for various plugins within the TensorRT ecosystem, and also fixed a segfault within the Normalize plugin. This indicates a strong involvement in maintaining and improving the functionality and stability of the TensorRT library, particularly related to plugin implementation.
deep-learninginferencenvidiatensorrtgpu-acceleration
Contributions:9 pushes, 12 branches in 1 year 3 months