lucadiliello / pytorch-apple-silicon-benchmarks
Performance of PyTorch on Apple Silicon
☆41Updated 9 months ago
Related projects: ⓘ
- example of using CoreML from c++☆21Updated last year
- Model compression for ONNX☆67Updated last week
- 3X speedup over Apple’s TensorFlow plugin by using Apache TVM on M1☆135Updated 2 years ago
- Code for "Training-free Graph Neural Networks and the Power of Labels as Features" (TMLR 2024)☆38Updated last month
- A user-friendly tool chain that enables the seamless execution of ONNX models using JAX as the backend.☆94Updated this week
- ☆64Updated 8 months ago
- mlx image models for Apple Silicon machines☆58Updated 4 months ago
- Mamba training library developed by kotoba technologies☆63Updated 7 months ago
- ONNX Runtime prebuilt wheels for Apple Silicon (M1 / M2 / M3 / ARM64)☆192Updated 2 months ago
- New operators for the ReferenceEvaluator, new kernels for onnxruntime, CPU, CUDA☆25Updated this week
- ☆46Updated 2 years ago
- ☆48Updated last year
- ONNX and TensorRT implementation of Whisper☆55Updated last year
- MLX support for the Open Neural Network Exchange (ONNX)☆34Updated 7 months ago
- C API for MLX☆68Updated last week
- TensorFlow Metal Backend on Apple Silicon Experiments (just for fun)☆272Updated 2 years ago
- Tools for simple inference testing using TensorRT, CUDA and OpenVINO CPU/GPU and CPU providers. Simple Inference Test for ONNX.☆18Updated 6 months ago
- A project that optimizes Whisper for low latency inference using NVIDIA TensorRT☆47Updated 2 months ago
- In-depth code associated with my Medium blog post, "How to Load PyTorch Models 340 Times Faster with Ray"☆24Updated 2 years ago
- Tune MPTs☆84Updated last year
- Python scripts performing optical flow estimation using the NeuFlowV2 model in ONNX.☆26Updated this week
- Benchmark of Apple MLX operations on all Apple Silicon chips (GPU, CPU) + MPS and CUDA.☆113Updated 2 weeks ago
- ☆56Updated 6 months ago
- ☆73Updated 5 months ago
- ☆101Updated this week
- Utilities for Training Very Large Models☆56Updated last week
- Checkpointable dataset utilities for foundation model training☆31Updated 7 months ago
- Tensors and Dynamic neural networks in Python with strong GPU acceleration☆17Updated last week
- CUDA implementation of autoregressive linear attention, with all the latest research findings☆43Updated last year
- Hacks for PyTorch☆17Updated last year