google/minimalloc
A lightweight memory allocator for hardware-accelerated machine learning
This tool helps hardware engineers and compiler developers efficiently manage memory for machine learning models running on specialized hardware. You provide a list of memory buffers with their required lifespans and sizes, and it outputs the optimal starting positions for these buffers in memory. This ensures the hardware accelerator can achieve its maximum performance.
180 stars. No commits in the last 6 months.
Use this if you are developing or optimizing compilers for machine learning workloads on hardware accelerators and need to perform static memory allocation.
Not ideal if you are a machine learning practitioner looking for a high-level library to train or deploy models, as this is a low-level compiler optimization tool.
Stars
180
Forks
15
Language
C++
License
Apache-2.0
Category
Last pushed
Sep 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/google/minimalloc"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
apache/tvm
Open Machine Learning Compiler Framework
uxlfoundation/oneDNN
oneAPI Deep Neural Network Library (oneDNN)
Tencent/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
OpenMined/TenSEAL
A library for doing homomorphic encryption operations on tensors
iree-org/iree-turbine
IREE's PyTorch Frontend, based on Torch Dynamo.