octoml / Apple-M1-BERT
3X speedup over Appleβs TensorFlow plugin by using Apache TVM on M1
β135Updated 2 years ago
Alternatives and similar repositories for Apple-M1-BERT:
Users that are interested in Apple-M1-BERT are comparing it to the libraries listed below
- 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
- benchmarking some transformer deploymentsβ26Updated 2 years ago
- Blazing fast training of π€ Transformers on Graphcore IPUsβ84Updated last year
- Home for OctoML PyTorch Profilerβ108Updated last year
- Fast sparse deep learning on CPUsβ52Updated 2 years ago
- Official code for "Distributed Deep Learning in Open Collaborations" (NeurIPS 2021)β116Updated 3 years ago
- Python bindings for ggmlβ140Updated 6 months ago
- Training material for IPU users: tutorials, feature examples, simple applicationsβ86Updated last year
- torch::deploy (multipy for non-torch uses) is a system that lets you get around the GIL problem by running multiple Python interpreters iβ¦β178Updated 3 months ago
- Implementation of a Transformer, but completely in Tritonβ260Updated 2 years ago
- Torch Distributed Experimentalβ115Updated 7 months ago
- PyTorch interface for the IPUβ177Updated last year
- This is a Tensor Train based compression library to compress sparse embedding tables used in large-scale machine learning models such as β¦β193Updated 2 years ago
- Swarm training framework using Haiku + JAX + Ray for layer parallel transformer language models on unreliable, heterogeneous nodesβ236Updated last year
- β87Updated 2 years ago
- β411Updated last year
- β67Updated 2 years ago
- Accelerate PyTorch models with ONNX Runtimeβ358Updated last month
- β116Updated 11 months ago
- GPTQ inference Triton kernelβ298Updated last year
- An open-source efficient deep learning framework/compiler, written in python.β690Updated last month
- DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight β¦β235Updated last year
- FlashAttention (Metal Port)β457Updated 6 months ago
- π Make Thinc faster on macOS by calling into Apple's native Accelerate libraryβ94Updated 5 months ago
- β290Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.β164Updated 2 weeks ago
- Customized matrix multiplication kernelsβ53Updated 3 years ago
- β55Updated 2 years ago
- The Triton backend for the PyTorch TorchScript models.β144Updated last week
- State of the art faster Transformer with Tensorflow 2.0 ( NLP, Computer Vision, Audio ).β85Updated 2 years ago