ROCm/Tensile
[DEPRECATED] Moved to ROCm/rocm-libraries repo
This tool generates high-performance building blocks for compute applications that run on AMD GPUs. It takes descriptions of matrix multiplications and N-dimensional tensor contractions, and outputs optimized code for these operations. Developers of scientific computing, machine learning, and other GPU-accelerated applications would use this.
257 stars.
Use this if you are a library developer creating high-performance computational kernels for AMD GPUs, especially for matrix and tensor operations.
Not ideal if you are an end-user running applications, as this is a foundational tool for library developers, not a direct application.
Stars
257
Forks
164
Language
Python
License
MIT
Category
Last pushed
Mar 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ROCm/Tensile"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
brucefan1983/GPUMD
Graphics Processing Units Molecular Dynamics
iree-org/iree
A retargetable MLIR-based machine learning compiler and runtime toolkit.
uxlfoundation/oneDAL
oneAPI Data Analytics Library (oneDAL)
rapidsai/cuml
cuML - RAPIDS Machine Learning Library
NVIDIA/cutlass
CUDA Templates and Python DSLs for High-Performance Linear Algebra