1.tracel-ai / burn
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
+47 stars
from 16,161 · score 3.87
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
9 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2.apache / tvm
Open Machine Learning Compiler Framework
+24 stars
from 13,862 · score 3.22
3.cupy / cupy
NumPy & SciPy for GPU
+10 stars
from 12,380 · score 2.40
4.ashvardanian / NumKong
SIMD-accelerated distances, dot products, matrix ops, geospatial & geometric kernels for 16 numeric types — from 6-bit floats to 64-bit complex — across x86, Arm, RISC-V, and WASM, with bindings for Python, Rust, C, C++, Swift, JS, and Go 📐
+7 stars
from 1,898 · score 2.08
5.chenyuntc / pytorch-book
PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch：入门与实战》)
+4 stars
from 12,843 · score 1.61
6.elixir-nx / nx
Multi-dimensional arrays (tensors) and numerical definitions for Elixir
+1 stars
from 2,918 · score 0.69
7.unslothai / hyperlearn
2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.
+1 stars
from 2,528 · score 0.69
8.vlang / vtl
The V Tensor Library
+1 stars
from 171 · score 0.69
9.born-ml / born
Born is a modern ML framework for Go — train and deploy models as single binaries. Pure Go, zero CGO, GPU accelerated.
+1 stars
from 137 · score 0.69