octoml / Apple-M1-BERT
3X speedup over Apple’s TensorFlow plugin by using Apache TVM on M1
☆135Updated 2 years ago
Related projects: ⓘ
- Nod.ai 🦈 version of 👻 . You probably want to start at https://github.com/nod-ai/shark for the product and the upstream IREE repository …☆107Updated this week
- benchmarking some transformer deployments☆26Updated last year
- ☆46Updated 2 years ago
- Distributed preprocessing and data loading for language datasets☆40Updated 5 months ago
- ☆110Updated 4 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 i…☆173Updated 3 months ago
- Fast sparse deep learning on CPUs☆51Updated last year
- Accelerate PyTorch models with ONNX Runtime☆353Updated 2 weeks ago
- Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)☆144Updated this week
- FlashAttention (Metal Port)☆358Updated 3 weeks ago
- Swarm training framework using Haiku + JAX + Ray for layer parallel transformer language models on unreliable, heterogeneous nodes☆236Updated last year
- Implementation of a Transformer, but completely in Triton☆242Updated 2 years ago
- This is a Tensor Train based compression library to compress sparse embedding tables used in large-scale machine learning models such as …☆192Updated 2 years ago
- Torch Distributed Experimental☆115Updated last month
- GPTQ inference Triton kernel☆273Updated last year
- Home for OctoML PyTorch Profiler☆105Updated last year
- Productionize machine learning predictions, with ONNX or without☆66Updated 8 months ago
- An open-source efficient deep learning framework/compiler, written in python.☆646Updated 3 weeks ago
- A performant, memory-efficient checkpointing library for PyTorch applications, designed with large, complex distributed workloads in mind…☆145Updated this week
- ☆411Updated 10 months ago
- ☆234Updated last month
- Customized matrix multiplication kernels☆53Updated 2 years ago
- Run transformers (incl. LLMs) on the Apple Neural Engine.☆51Updated 9 months ago
- ☆127Updated 2 years ago
- Python bindings for ggml☆125Updated 2 weeks ago
- Training material for IPU users: tutorials, feature examples, simple applications☆86Updated last year
- The Triton backend for the PyTorch TorchScript models.☆117Updated last week
- Simple and fast low-bit matmul kernels in CUDA☆48Updated this week
- Blazing fast training of 🤗 Transformers on Graphcore IPUs☆81Updated 6 months ago
- DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight …☆229Updated last year