IBM / onnx-mlir-servingLinks
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.
☆25Updated 2 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
Sorting:
- A lightweight, Pythonic, frontend for MLIR☆80Updated 2 years ago
- ☆50Updated last year
- Efficient in-memory representation for ONNX, in Python☆34Updated last week
- Unified compiler/runtime for interfacing with PyTorch Dynamo.☆104Updated last week
- C++ implementations for various tokenizers (sentencepiece, tiktoken etc).☆43Updated this week
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆47Updated 3 months ago
- Notes and artifacts from the ONNX steering committee☆27Updated 2 weeks ago
- Collection of scripts to build PyTorch and the domain libraries from source.☆12Updated last month
- ☆170Updated 3 weeks ago
- Play with MLIR right in your browser☆138Updated 2 years ago
- Common utilities for ONNX converters☆288Updated 3 months ago
- ☆24Updated last year
- This is a demo how to write a high performance convolution run on apple silicon☆57Updated 3 years ago
- Experiments and prototypes associated with IREE or MLIR☆55Updated last year
- Python interface for MLIR - the Multi-Level Intermediate Representation☆270Updated last year
- MatMul Performance Benchmarks for a Single CPU Core comparing both hand engineered and codegen kernels.☆138Updated 2 years ago
- TORCH_LOGS parser for PT2☆69Updated last month
- torch::deploy (multipy for non-torch uses) is a system that lets you get around the GIL problem by running multiple Python interpreters i…☆182Updated 3 months ago
- Open source cross-platform compiler for compute-intensive loops used in AI algorithms, from Microsoft Research☆113Updated 2 years ago
- A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")☆363Updated this week
- ☆422Updated last week
- Standalone Flash Attention v2 kernel without libtorch dependency☆112Updated last year
- MLIR-based partitioning system☆151Updated last week
- Conversions to MLIR EmitC☆134Updated 11 months ago
- IREE's PyTorch Frontend, based on Torch Dynamo.☆102Updated this week
- ☆318Updated 2 weeks ago
- Visualize ONNX models with model-explorer☆64Updated last month
- ☆68Updated 2 years ago
- Inference Vision Transformer (ViT) in plain C/C++ with ggml☆300Updated last year
- Header-only safetensors loader and saver in C++☆72Updated 7 months ago