AndreSlavescu/meTile
python-based eDSL for efficient Metal Shading Language code generation
This project helps high-performance computing developers write specialized matrix operations and other numerical kernels that run efficiently on Apple GPUs. You write Python code using a domain-specific language (DSL) to describe these operations, which is then compiled into highly optimized Metal Shading Language (MSL). The output is a precompiled Metal library that can be dispatched from Python, allowing researchers and engineers to accelerate their numerical workloads.
Use this if you need to develop custom, high-performance numerical kernels specifically for Apple GPUs and prefer to work in Python rather than directly in Metal Shading Language.
Not ideal if you are looking for a general-purpose GPU programming solution that works across different hardware vendors (NVIDIA, AMD) or if you are not comfortable with low-level kernel optimization concepts.
Stars
11
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AndreSlavescu/meTile"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
iree-org/iree
A retargetable MLIR-based machine learning compiler and runtime toolkit.
brucefan1983/GPUMD
Graphics Processing Units Molecular Dynamics
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