ONNX Serving is a project written with C++ to serve onnx-mlir compiled models with GRPC and other protocols.Benefiting from C++ implementation, ONNX Serving has very low latency overhead and high throughput. ONNX Servring provides dynamic batch aggregation and workers pool to fully utilize AI accelerators on the machine.
☆25Sep 17, 2025Updated 10 months ago
Alternatives and similar repositories for onnx-mlir-serving
Users that are interested in onnx-mlir-serving are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The Gstreamer hardware encoder/decoder plugins for Rockchip platform☆13Oct 8, 2023Updated 2 years ago
- Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure☆1,040Updated this week
- A sandbox for quick iteration and experimentation on projects related to IREE, MLIR, and LLVM☆62Apr 13, 2026Updated 4 months ago
- edge/mobile transformer based Vision DNN inference benchmark☆16Aug 29, 2025Updated 11 months ago
- ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.☆451Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Python versioned abstract syntax trees and interface to the Python parser☆13Oct 28, 2022Updated 3 years ago
- Tutorial on how to convert machine learned models into ONNX☆14Mar 11, 2023Updated 3 years ago
- Common utilities for ONNX converters☆304Updated this week
- ☆15Apr 15, 2022Updated 4 years ago
- The Triton backend for the ONNX Runtime.☆186Updated this week
- Scoreboard for ONNX Backend Compatibility☆29Aug 6, 2026Updated last week
- Benchmark scripts for TVM☆75Mar 15, 2022Updated 4 years ago
- ☆11Apr 5, 2021Updated 5 years ago
- AnyDSL traversal code☆15Feb 18, 2019Updated 7 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Convert StableHLO models into Apple Core ML format☆22Jun 28, 2026Updated last month
- Distributed machine learning platform☆13Aug 20, 2015Updated 10 years ago
- Capture image & output the file with specified camera. This is utility for screenshot, transparent texture.☆13May 13, 2021Updated 5 years ago
- This is an obsolete version of LASP. Use the latest version 👉☆11Jul 18, 2017Updated 9 years ago
- Example of verifying cryptographically signed and encrypted license files using C++, OpenSSL, Ed25519 and AES-256-GCM.☆12Dec 8, 2023Updated 2 years ago
- unity调用打印机☆10Jul 28, 2017Updated 9 years ago
- Documentations for RELION☆15Updated this week
- GFPGAN face reconstruction with ncnn on a bare Raspberry Pi☆14Jan 4, 2023Updated 3 years ago
- Window capture plugin for Unity☆14Nov 18, 2016Updated 9 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Remote source nodes for NNStreamer pipelines without GStreamer dependencies☆17Mar 11, 2026Updated 5 months ago
- Directshow Audio Loopback Capture Filter☆12Jan 17, 2014Updated 12 years ago
- onnxruntime-extensions: A specialized pre- and post- processing library for ONNX Runtime☆474Updated this week
- 关于无锁队列的知识☆11Feb 13, 2017Updated 9 years ago
- Complete solution to enable RDMA (on both InfiniBand and RoCE) and accelerate TCP to bare metal performance on Kubernetes☆11Aug 1, 2018Updated 8 years ago
- ☆14Jul 21, 2022Updated 4 years ago
- A SapientML plugin of SapientMLGenerator☆11Jul 27, 2026Updated 2 weeks ago
- example of using CoreML from c++☆24Jun 14, 2023Updated 3 years ago
- A PyTorch implementation of "Self-Supervised GNN that Jointly Learns to Augment" or "Jointly Learnable Data Augmentations for Self-Superv…☆13Dec 13, 2021Updated 4 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Simple Arm assembly kernels for testing the performance and functionality of Arm CPUs.☆16Dec 3, 2023Updated 2 years ago
- A GitHub Action to run a cpplint command when new code is pushed into your repo☆12Mar 24, 2025Updated last year
- A customisable GitHub action to check the style of Python code with black.☆12May 20, 2024Updated 2 years ago
- AI applications and tools☆30Updated this week
- Run cpplint with reviewdog☆13Aug 7, 2026Updated last week
- Notes and artifacts from the ONNX steering committee☆29Updated this week
- ☆11Jan 7, 2023Updated 3 years ago