leimao / Simple-Inference-Server
Inference Server Implementation from Scratch for Machine Learning Models
☆24Updated 4 years ago
Alternatives and similar repositories for Simple-Inference-Server:
Users that are interested in Simple-Inference-Server are comparing it to the libraries listed below
- ONNX Command-Line Toolbox☆35Updated 6 months ago
- Personal collection of references for high performance mixed precision training.☆41Updated 5 years ago
- Fast sparse deep learning on CPUs☆53Updated 2 years ago
- Distributed DataLoader For Pytorch Based On Ray☆24Updated 3 years ago
- Fairring (FAIR + Herring) is a plug-in for PyTorch that provides a process group for distributed training that outperforms NCCL at large …☆65Updated 3 years ago
- DLPack for Tensorflow☆35Updated 5 years ago
- Customized matrix multiplication kernels☆54Updated 3 years ago
- An Open Convolutional Neural Network Framework in C++ From Scratch☆61Updated 4 years ago
- Artifacts for SOSP'19 paper Optimizing Deep Learning Computation with Automatic Generation of Graph Substitutions☆21Updated 3 years ago
- This is the (evolving) reading list for the seminar.☆57Updated 4 years ago
- Distributed ML Optimizer☆32Updated 3 years ago
- Benchmarking PyTorch 2.0 different models☆21Updated 2 years ago
- Inference framework for MoE layers based on TensorRT with Python binding☆41Updated 3 years ago
- A GPU performance profiling tool for PyTorch models☆22Updated 2 years ago
- A Ray-based data loader with per-epoch shuffling and configurable pipelining, for shuffling and loading training data for distributed tra…☆18Updated 2 years ago
- A boilerplate to use multiprocessing for your gRPC server in your Python project☆25Updated 3 years ago
- Codebase associated with the PyTorch compiler tutorial☆45Updated 5 years ago
- PyProf2: PyTorch Profiling tool☆82Updated 4 years ago
- On Intrinsic Dataset Properties for Adversarial Machine Learning☆19Updated 4 years ago
- Context Manager to profile the forward and backward times of PyTorch's nn.Module☆83Updated last year
- torch::deploy (multipy for non-torch uses) is a system that lets you get around the GIL problem by running multiple Python interpreters i…☆180Updated 4 months ago
- Runtime Tracing Library for TensorFlow☆43Updated 6 years ago
- No-GIL Python environment featuring NVIDIA Deep Learning libraries.☆57Updated last week
- benchmarking some transformer deployments☆26Updated 2 years ago
- Training neural networks in TensorFlow 2.0 with 5x less memory☆130Updated 3 years ago
- Code for Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture (accepted by PVLDB).The outdated wr…☆9Updated last year
- ☆14Updated 3 years ago
- ☆69Updated 2 years ago
- Example workflow for our data-centric speech benchmark☆17Updated last year
- ☆22Updated 5 years ago