octoml / Apple-M1-BERTLinks
3X speedup over Appleβs TensorFlow plugin by using Apache TVM on M1
β137Updated 3 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
Sorting:
- 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 8 months ago
- benchmarking some transformer deploymentsβ26Updated 2 years ago
- Official code for "Distributed Deep Learning in Open Collaborations" (NeurIPS 2021)β117Updated 3 years ago
- Torch Distributed Experimentalβ117Updated last year
- Training material for IPU users: tutorials, feature examples, simple applicationsβ87Updated 2 years ago
- DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.β168Updated 2 months ago
- PyTorch interface for the IPUβ181Updated last year
- Blazing fast training of π€ Transformers on Graphcore IPUsβ86Updated last year
- Example code and applications for machine learning on Graphcore IPUsβ330Updated last year
- β67Updated 3 years ago
- DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight β¦β236Updated 2 years ago
- Tutorial on how to convert machine learned models into ONNXβ16Updated 2 years ago
- This repository contains example code to build models on TPUsβ30Updated 2 years ago
- Accelerate PyTorch models with ONNX Runtimeβ364Updated 7 months ago
- β131Updated 3 years ago
- Babysit your preemptible TPUsβ86Updated 2 years ago
- Swarm training framework using Haiku + JAX + Ray for layer parallel transformer language models on unreliable, heterogeneous nodesβ241Updated 2 years ago
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)β189Updated 3 years ago
- Customized matrix multiplication kernelsβ56Updated 3 years ago
- Implementation of a Transformer, but completely in Tritonβ274Updated 3 years ago
- β252Updated 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¦β181Updated 3 weeks ago
- The elegant integration of huggingface/nlp and fastai2 and handy transforms using pure huggingface/nlpβ19Updated 4 years ago
- experiments with inference on llamaβ104Updated last year
- β39Updated 2 years ago
- π Make Thinc faster on macOS by calling into Apple's native Accelerate libraryβ101Updated 2 months ago
- β91Updated 3 years ago
- Python bindings for ggmlβ146Updated last year
- Experiments with generating opensource language model assistantsβ97Updated 2 years ago
- Fast sparse deep learning on CPUsβ56Updated 2 years ago