nod-ai / transformer-benchmarks
benchmarking some transformer deployments
β26Updated last year
Alternatives and similar repositories for transformer-benchmarks:
Users that are interested in transformer-benchmarks are comparing it to the libraries listed below
- Benchmarks to capture important workloads.β29Updated last month
- β12Updated 3 years ago
- 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 β¦β106Updated 2 months ago
- A tracing JIT compiler for PyTorchβ13Updated 3 years ago
- Torch Distributed Experimentalβ115Updated 7 months ago
- Fast sparse deep learning on CPUsβ52Updated 2 years ago
- Fairring (FAIR + Herring) is a plug-in for PyTorch that provides a process group for distributed training that outperforms NCCL at large β¦β63Updated 2 years ago
- Distributed ML Optimizerβ30Updated 3 years ago
- MLPerfβ’ logging libraryβ33Updated last week
- Tutorial on how to convert machine learned models into ONNXβ16Updated 2 years ago
- β62Updated 3 weeks ago
- Distributed preprocessing and data loading for language datasetsβ39Updated 11 months ago
- Make triton easierβ47Updated 9 months ago
- Training neural networks in TensorFlow 2.0 with 5x less memoryβ130Updated 3 years ago
- Notes and artifacts from the ONNX steering committeeβ25Updated 2 weeks ago
- A library for syntactically rewriting Python programs, pronounced (sinner).β70Updated 3 years ago
- β51Updated 7 months ago
- Stride visualizationsβ37Updated 6 years ago
- Codebase associated with the PyTorch compiler tutorialβ46Updated 5 years ago
- Home for OctoML PyTorch Profilerβ108Updated last year
- Implementation of a Tensorflow XLA rematerialization passβ15Updated 5 years ago
- Inference framework for MoE layers based on TensorRT with Python bindingβ41Updated 3 years ago
- Some microbenchmarks and design docs before commencementβ12Updated 4 years ago
- A lightweight wrapper for PyTorch that provides a simple declarative API for context switching between devices, distributed modes, mixed-β¦β67Updated last year
- β23Updated last year
- β27Updated 2 months ago
- β14Updated last year
- PyTorch RFCs (experimental)β130Updated 6 months ago
- Memory Optimizations for Deep Learning (ICML 2023)β62Updated last year
- SParse AcceleRation on Tensor Architectureβ17Updated 5 months ago