nod-ai / SRT
Nod.ai π¦ version of π» . You probably want to start at https://github.com/nod-ai/shark for the product and the upstream IREE repository for mainline development. This repository houses branches and configuration that aren't ready for commit upstream.
β106Updated 3 months ago
Alternatives and similar repositories for SRT:
Users that are interested in SRT are comparing it to the libraries listed below
- benchmarking some transformer deploymentsβ26Updated 2 years ago
- A thin, highly portable toolkit for efficiently compiling dense loop-based computation.β148Updated 2 years ago
- β51Updated 8 months ago
- MLIR-based partitioning systemβ80Updated last week
- Home for OctoML PyTorch Profilerβ112Updated 2 years ago
- A tracing JIT compiler for PyTorchβ13Updated 3 years ago
- Fast sparse deep learning on CPUsβ53Updated 2 years ago
- Training neural networks in TensorFlow 2.0 with 5x less memoryβ130Updated 3 years ago
- β13Updated 3 years ago
- β50Updated last year
- Benchmarks to capture important workloads.β31Updated 2 months ago
- A Data-Centric Compiler for Machine Learningβ82Updated last year
- Customized matrix multiplication kernelsβ54Updated 3 years ago
- A lightweight, Pythonic, frontend for MLIRβ81Updated last year
- Python interface for MLIR - the Multi-Level Intermediate Representationβ254Updated 4 months ago
- PyTorch interface for the IPUβ179Updated last year
- Unified compiler/runtime for interfacing with PyTorch Dynamo.β99Updated 2 months ago
- torch::deploy (multipy for non-torch uses) is a system that lets you get around the GIL problem by running multiple Python interpreters iβ¦β180Updated 4 months ago
- MatMul Performance Benchmarks for a Single CPU Core comparing both hand engineered and codegen kernels.β130Updated last year
- High-Performance SGEMM on CUDA devicesβ90Updated 3 months ago
- Repository for the QUIK project, enabling the use of 4bit kernels for generative inference - EMNLP 2024β179Updated last year
- A performant, memory-efficient checkpointing library for PyTorch applications, designed with large, complex distributed workloads in mindβ¦β156Updated 4 months ago
- 3X speedup over Appleβs TensorFlow plugin by using Apache TVM on M1β136Updated 3 years ago
- Stores documents and resources used by the OpenXLA developer communityβ120Updated 8 months ago
- A schedule language for large model trainingβ146Updated 10 months ago
- Torch Distributed Experimentalβ115Updated 8 months ago
- IREE's PyTorch Frontend, based on Torch Dynamo.β79Updated this week
- Backward compatible ML compute opset inspired by HLO/MHLOβ467Updated this week
- A stand-alone implementation of several NumPy dtype extensions used in machine learning.β258Updated this week
- π Interactive performance profiling and debugging tool for PyTorch neural networks.β61Updated 3 months ago