triton-inference-server / coreLinks
The core library and APIs implementing the Triton Inference Server.
☆137Updated this week
Alternatives and similar repositories for core
Users that are interested in core are comparing it to the libraries listed below
Sorting:
- Common source, scripts and utilities for creating Triton backends.☆327Updated this week
- The Triton backend for the ONNX Runtime.☆152Updated this week
- Common source, scripts and utilities shared across all Triton repositories.☆74Updated this week
- Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Serv…☆477Updated 2 weeks ago
- Triton Model Navigator is an inference toolkit designed for optimizing and deploying Deep Learning models with a focus on NVIDIA GPUs.☆205Updated 2 months ago
- The Triton backend for TensorRT.☆77Updated this week
- ☆50Updated 3 months ago
- NVIDIA Inference Xfer Library (NIXL)☆422Updated this week
- HierarchicalKV is a part of NVIDIA Merlin and provides hierarchical key-value storage to meet RecSys requirements. The key capability of…☆152Updated this week
- ☆267Updated 2 weeks ago
- Triton Python, C++ and Java client libraries, and GRPC-generated client examples for go, java and scala.☆629Updated this week
- The Triton backend for the PyTorch TorchScript models.☆152Updated this week
- ☆81Updated this week
- Fast and memory-efficient exact attention☆74Updated last week
- Common utilities for ONNX converters☆272Updated 6 months ago
- A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")☆337Updated this week
- The Triton backend that allows running GPU-accelerated data pre-processing pipelines implemented in DALI's python API.☆135Updated 3 weeks ago
- KV cache store for distributed LLM inference☆269Updated 2 weeks ago
- The Triton backend for TensorFlow.☆52Updated this week
- TePDist (TEnsor Program DISTributed) is an HLO-level automatic distributed system for DL models.☆94Updated 2 years ago
- FIL backend for the Triton Inference Server☆81Updated 2 weeks ago
- Triton CLI is an open source command line interface that enables users to create, deploy, and profile models served by the Triton Inferen…☆64Updated 2 weeks ago
- Universal cross-platform tokenizers binding to HF and sentencepiece☆346Updated last week
- NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.☆116Updated last year
- NVIDIA NCCL Tests for Distributed Training☆97Updated this week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆379Updated this week
- oneAPI Collective Communications Library (oneCCL)☆237Updated last week
- NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs☆532Updated last month
- ☆26Updated 3 months ago
- PyTorch distributed training acceleration framework☆49Updated 4 months ago