nod-ai / SRTLinks
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 6 months ago
Alternatives and similar repositories for SRT
Users that are interested in SRT are comparing it to the libraries listed below
Sorting:
- benchmarking some transformer deploymentsβ26Updated 2 years ago
- 3X speedup over Appleβs TensorFlow plugin by using Apache TVM on M1β136Updated 3 years ago
- A tracing JIT compiler for PyTorchβ13Updated 3 years ago
- A thin, highly portable toolkit for efficiently compiling dense loop-based computation.β148Updated 2 years ago
- PyTorch interface for the IPUβ180Updated last year
- Customized matrix multiplication kernelsβ56Updated 3 years ago
- GPU implementation of a fast generalized ANS (asymmetric numeral system) entropy encoder and decoder, with extensions for lossless compreβ¦β345Updated last month
- A stand-alone implementation of several NumPy dtype extensions used in machine learning.β284Updated 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 iβ¦β180Updated 3 weeks ago
- β52Updated 11 months ago
- PyTorch RFCs (experimental)β134Updated 2 months ago
- Benchmarks to capture important workloads.β31Updated 6 months ago
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.β46Updated last year
- Home for OctoML PyTorch Profilerβ113Updated 2 years ago
- Tutorial on how to convert machine learned models into ONNXβ16Updated 2 years ago
- Torch Distributed Experimentalβ117Updated last year
- β74Updated last year
- A user-friendly tool chain that enables the seamless execution of ONNX models using JAX as the backend.β118Updated this week
- A Data-Centric Compiler for Machine Learningβ84Updated last year
- Training neural networks in TensorFlow 2.0 with 5x less memoryβ132Updated 3 years ago
- Repository for the QUIK project, enabling the use of 4bit kernels for generative inference - EMNLP 2024β181Updated last year
- The Foundation for All Legate Librariesβ219Updated this week
- A library for syntactically rewriting Python programs, pronounced (sinner).β69Updated 3 years ago
- A tensor-aware point-to-point communication primitive for machine learningβ259Updated 2 years ago
- Fast sparse deep learning on CPUsβ54Updated 2 years ago
- A performant, memory-efficient checkpointing library for PyTorch applications, designed with large, complex distributed workloads in mindβ¦β158Updated last month
- A tracing JIT for PyTorchβ17Updated 2 years ago
- β13Updated 4 years ago
- PyTorch centric eager mode debuggerβ47Updated 7 months ago
- Standalone commandline CLI tool for compiling Triton kernelsβ17Updated 10 months ago