nod.ai

High Performance Machine Learning

United States of America

Pinned Repositories

iree-amd-aie
IREE plugin repository for the AMD AIE accelerator
Language:MLIR64 23 14929
llama
Inference code for LLaMA models
Language:Python8 1 01
pandas-mlir
Bridging Pandas and MLIR ecosystems
Language:C++17 4 01
PI
A lightweight MLIR Python frontend with support for PyTorch
Language:C++19 18 14
SHARK
SHARK - High Performance Machine Learning Distribution
Language:Python1.4k 41 562168
SHARK-Turbine
Unified compiler/runtime for interfacing with PyTorch Dynamo.
Language:Python92 32 54546
sharktank
SHARK Inference Modeling and Serving
Language:Python9 16 2814
SRT
Nod.ai 🦈 version of 👻 . You probably want to start at https://github.com/nod-ai/shark for the product and the upstream IREE repository for mainline development. This repository houses branches and configuration that aren't ready for commit upstream.
Language:C++107 3 511
techtalks
16 5 00
transformer-benchmarks
benchmarking some transformer deployments
Language:Python26 3 312

nod.ai's Repositories

nod-ai/SHARK
SHARK - High Performance Machine Learning Distribution
Language:Python1.4k 41 562168
nod-ai/SRT
Nod.ai 🦈 version of 👻 . You probably want to start at https://github.com/nod-ai/shark for the product and the upstream IREE repository for mainline development. This repository houses branches and configuration that aren't ready for commit upstream.
Language:C++107 3 511
nod-ai/SHARK-Turbine
Unified compiler/runtime for interfacing with PyTorch Dynamo.
Language:Python92 32 54546
nod-ai/iree-amd-aie
IREE plugin repository for the AMD AIE accelerator
Language:MLIR64 23 14929
nod-ai/PI
A lightweight MLIR Python frontend with support for PyTorch
Language:C++19 18 14
nod-ai/pandas-mlir
Bridging Pandas and MLIR ecosystems
Language:C++17 4 01
nod-ai/techtalks
16 5 00
nod-ai/sharktank
SHARK Inference Modeling and Serving
Language:Python9 16 2814
nod-ai/TheRock
The HIP Environment and ROCm Kit - A lightweight open source build system for HIP and ROCm
Language:CMake5 4 22
nod-ai/mlir-aie
An MLIR-based toolchain for AMD AI Engine-enabled devices.
Language:MLIR4 1 02
nod-ai/torch-mlir
The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.
Language:C++3 1 02
nod-ai/ROCR-Runtime
(fork) ROCm Platform Runtime: ROCr a HPC market enhanced HSA based runtime
Language:C++20
nod-ai/sdxl-scripts
Language:MLIR2 4 206
nod-ai/SHARK-TestSuite
Temporary home of a test suite we are evaluating
Language:Python2 11 6926
nod-ai/convperf
Language:C++1 4 02
nod-ai/mlir-air
Fork of the upstream mlir-air repository for dependency management.
Language:C++1 1 01
nod-ai/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Language:C++1 1 03
nod-ai/prototype-aie-toolchain
AIE-RT + Python
Language:Python1 14 0
nod-ai/rocm-gemm-benchmark
Language:MLIR11
nod-ai/llm-dev
Temporary repo for llm development.
Language:MLIR01
nod-ai/base-docker-images
Utility repository for publishing docker images that we depend on.
Language:Shell16 03
nod-ai/diffusers
🤗 Diffusers for SHARK
Language:Python1 01
nod-ai/e2eshark-reports
5 0
nod-ai/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Language:Python1 0
nod-ai/ROCm
Shared Fork of ROCm repository for development
Language:Python0 0
nod-ai/SHARK-devtools
Development tools for managing SHARK projects.
Language:Python4 0
nod-ai/stablehlo
Backward compatible ML compute opset inspired by HLO/MHLO
Language:MLIR1 01
nod-ai/vllm_backend
Triton Inference Server vLLM Backend
nod-ai/xla
A machine learning compiler for GPUs, CPUs, and ML accelerators
Language:C++1 01
nod-ai/XRT
(fork) Run Time for AIE and FPGA based platforms
Language:C++