tenstorrent / tt-buda
Tenstorrent TT-BUDA Repository
☆220Updated last month
Related projects ⓘ
Alternatives and complementary repositories for tt-buda
- TT-NN operator library, and TT-Metalium low level kernel programming model.☆466Updated this week
- Tenstorrent MLIR compiler☆72Updated this week
- Repository of model demos using TT-Buda☆55Updated last week
- Buda Compiler Backend for Tenstorrent devices☆25Updated last month
- An MLIR-based toolchain for AMD AI Engine-enabled devices.☆305Updated this week
- TVM for Tenstorrent ASICs☆20Updated this week
- Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators☆309Updated this week
- PyTorch emulation library for Microscaling (MX)-compatible data formats☆162Updated last month
- IREE plugin repository for the AMD AIE accelerator☆66Updated this week
- OpenAI Triton backend for Intel® GPUs☆143Updated this week
- ⭐️ TTNN Compiler for PyTorch 2.0 ⭐️ It enables running PyTorch2.0 models on Tenstorrent hardware☆25Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆407Updated this week
- Shared Middle-Layer for Triton Compilation☆185Updated this week
- Backward compatible ML compute opset inspired by HLO/MHLO☆408Updated this week
- An experimental CPU backend for Triton☆55Updated last week
- Intel® Extension for MLIR. A staging ground for MLIR dialects and tools for Intel devices using the MLIR toolchain.☆123Updated this week
- Stores documents and resources used by the OpenXLA developer community☆106Updated 3 months ago
- IREE's PyTorch Frontend, based on Torch Dynamo.☆53Updated this week
- Tenstorrent Kernel Module☆32Updated last month
- The Riallto Open Source Project from AMD☆68Updated last week
- Unified compiler/runtime for interfacing with PyTorch Dynamo.☆95Updated this week
- CUDA Matrix Multiplication Optimization☆139Updated 3 months ago
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆34Updated 5 months ago
- hipBLASLt is a library that provides general matrix-matrix operations with a flexible API and extends functionalities beyond a traditiona…☆60Updated this week
- ☆79Updated this week
- Machine-Learning Accelerator System Exploration Tools☆121Updated this week
- Fork of LLVM to support AMD AIEngine processors☆107Updated this week
- HeteroCL: A Multi-Paradigm Programming Infrastructure for Software-Defined Heterogeneous Computing☆325Updated 6 months ago
- GPUOcelot: A dynamic compilation framework for PTX☆145Updated last month
- A tool for generating information about the matrix multiplication instructions in AMD Radeon™ and AMD Instinct™ accelerators☆65Updated 10 months ago