HabanaAI / SynapseAI_CoreLinks
SynapseAI Core is a reference implementation of the SynapseAI API running on Habana Gaudi
☆41Updated 4 months ago
Alternatives and similar repositories for SynapseAI_Core
Users that are interested in SynapseAI_Core are comparing it to the libraries listed below
Sorting:
- oneCCL Bindings for Pytorch*☆97Updated last month
- Bandwidth test for ROCm☆56Updated 2 weeks ago
- ROCm Tracer Callback/Activity Library for Performance tracing AMD GPUs☆83Updated last week
- ☆71Updated 2 months ago
- A CUTLASS implementation using SYCL☆23Updated this week
- ☆36Updated this week
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆43Updated 2 months ago
- MLIR-based partitioning system☆86Updated this week
- ☆50Updated last year
- OpenAI Triton backend for Intel® GPUs☆187Updated this week
- Intel® Extension for DeepSpeed* is an extension to DeepSpeed that brings feature support with SYCL kernels on Intel GPU(XPU) device. Note…☆61Updated 3 months ago
- oneAPI Collective Communications Library (oneCCL)☆234Updated 2 weeks ago
- ☆80Updated 6 months ago
- ☆146Updated this week
- Intel® SHMEM - Device initiated shared memory based communication library☆23Updated 2 months ago
- Provides the examples to write and build Habana custom kernels using the HabanaTools☆21Updated last month
- Explore training for quantized models☆18Updated this week
- A sandbox for quick iteration and experimentation on projects related to IREE, MLIR, and LLVM☆57Updated 2 months ago
- Benchmarks to capture important workloads.☆31Updated 4 months ago
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆13Updated 2 weeks ago
- ROCm BLAS marshalling library☆142Updated this week
- RCCL Performance Benchmark Tests☆67Updated 2 weeks ago
- ☆46Updated this week
- A tracing JIT for PyTorch☆17Updated 2 years ago
- OpenVINO Intel NPU Compiler☆56Updated this week
- Unified compiler/runtime for interfacing with PyTorch Dynamo.☆100Updated 2 weeks ago
- hipBLASLt is a library that provides general matrix-matrix operations with a flexible API and extends functionalities beyond a traditiona…☆97Updated this week
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆88Updated last week
- AMD's graph optimization engine.☆220Updated this week
- An extension library of WMMA API (Tensor Core API)☆97Updated 10 months ago