1.pytorch / pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
+3,330 stars
from 101,740 · score 8.11
Trending repositories
Ranked by Attention Score: stars gained over the last 90 complete days
14 repositories by Attention Score · Aug 5, 2026 – Nov 2, 2026 (UTC)
2.tracel-ai / burn
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
+570 stars
from 15,638 · score 6.35
3.apache / tvm
Open Machine Learning Compiler Framework
+275 stars
from 13,611 · score 5.62
4.cupy / cupy
NumPy & SciPy for GPU
+192 stars
from 12,198 · score 5.26
5.unslothai / hyperlearn
2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.
+48 stars
from 2,481 · score 3.89
6.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 📐
+48 stars
from 1,857 · score 3.89
7.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》)
+41 stars
from 12,806 · score 3.74
8.elixir-nx / nx
Multi-dimensional arrays (tensors) and numerical definitions for Elixir
+23 stars
from 2,896 · score 3.18
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.
+21 stars
from 117 · score 3.09
10.vlang / vtl
The V Tensor Library
+7 stars
from 165 · score 2.08
11.LaurentMazare / ocaml-torch
OCaml bindings for PyTorch
+2 stars
from 442 · score 1.10
12.georgebuilds / anneal
Machine learning compiler in Go. A from-scratch tinygrad port: graph-rewrite IR, autodiff as a compiler pass, zero-CGO WebGPU backend.
+2 stars
from 31 · score 1.10
13.DiffSharp / DiffSharp
DiffSharp: Differentiable Functional Programming
+1 stars
from 615 · score 0.69
14.seung-lab / cloud-volume
Read and write Neuroglancer datasets programmatically.
+1 stars
from 175 · score 0.69