triton-inference-server / pytorch_backendLinks
The Triton backend for the PyTorch TorchScript models.
☆157Updated last week
Alternatives and similar repositories for pytorch_backend
Users that are interested in pytorch_backend are comparing it to the libraries listed below
Sorting:
- The Triton backend for the ONNX Runtime.☆156Updated last week
- 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 3 weeks ago
- Triton Model Navigator is an inference toolkit designed for optimizing and deploying Deep Learning models with a focus on NVIDIA GPUs.☆210Updated 3 months ago
- A performant, memory-efficient checkpointing library for PyTorch applications, designed with large, complex distributed workloads in mind…☆158Updated last month
- Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Serv…☆482Updated last week
- The Triton backend for TensorRT.☆77Updated this week
- Common source, scripts and utilities for creating Triton backends.☆336Updated last week
- Torch Distributed Experimental☆117Updated 11 months ago
- PyTorch RFCs (experimental)☆133Updated 2 months ago
- Implementation of a Transformer, but completely in Triton☆273Updated 3 years ago
- TorchX is a universal job launcher for PyTorch applications. TorchX is designed to have fast iteration time for training/research and sup…☆378Updated this week
- ☆120Updated last year
- Home for OctoML PyTorch Profiler☆113Updated 2 years ago
- Distributed preprocessing and data loading for language datasets☆39Updated last year
- Accelerate PyTorch models with ONNX Runtime☆364Updated 5 months ago
- Reference models for Intel(R) Gaudi(R) AI Accelerator☆167Updated last week
- ☆251Updated last year
- ☆280Updated this week
- Triton CLI is an open source command line interface that enables users to create, deploy, and profile models served by the Triton Inferen…☆64Updated last week
- Provide Python access to the NVML library for GPU diagnostics☆242Updated 8 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆206Updated last week
- PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.☆813Updated last month
- A library to analyze PyTorch traces.☆400Updated this week
- A tensor-aware point-to-point communication primitive for machine learning☆259Updated 2 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
- The Triton backend that allows running GPU-accelerated data pre-processing pipelines implemented in DALI's python API.☆136Updated last week
- Easy and Efficient Quantization for Transformers☆198Updated last month
- Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)☆191Updated this week
- ☆74Updated 4 months ago
- oneCCL Bindings for Pytorch*☆99Updated 3 weeks ago