Tensor Computation Libraries ML Frameworks

C++ and multi-language libraries providing core tensor operations, linear algebra, and multidimensional array manipulation for machine learning. Does NOT include end-to-end deep learning frameworks, neural network layers, or domain-specific applications—focus is on low-level tensor primitives and algebraic optimizations.

There are 120 tensor computation libraries frameworks tracked. 4 score above 70 (verified tier). The highest-rated is apache/tvm at 75/100 with 13,183 stars and 11 monthly downloads. 3 of the top 10 are actively maintained.

Get all 120 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=tensor-computation-libraries&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Framework	Score	Tier	Stars	Language
1	apache/tvm Open Machine Learning Compiler Framework	75	Verified	13,183	Python
2	uxlfoundation/oneDNN oneAPI Deep Neural Network Library (oneDNN)	73	Verified	3,962	C++
3	Tencent/ncnn ncnn is a high-performance neural network inference framework optimized for...	71	Verified	22,890	C++
4	OpenMined/TenSEAL A library for doing homomorphic encryption operations on tensors	70	Verified	1,006	C++
5	iree-org/iree-turbine IREE's PyTorch Frontend, based on Torch Dynamo.	67	Established	105	Python
6	ARM-software/armnn Arm NN ML Software.	61	Established	1,299	C++
7	VeriSilicon/TIM-VX VeriSilicon Tensor Interface Module	59	Established	250	C
8	lisitsyn/tapkee A flexible and efficient С++ template library for dimension reduction	58	Established	234	C++
9	dmlc/dlpack common in-memory tensor structure	58	Established	1,178	C++
10	koba-jon/pytorch_cpp Deep Learning sample programs using PyTorch in C++	58	Established	309	C++
11	libxsmm/tpp-mlir TPP experimentation on MLIR for linear algebra	57	Established	146	MLIR
12	apache/tvm-ffi Open ABI and FFI for Machine Learning Systems	57	Established	361	C++
13	XUANTIE-RV/csi-nn2 An optimized neural network operator library for chips base on Xuantie CPU.	56	Established	99	C
14	keith2018/TinyTorch A tiny deep learning training framework implemented from scratch in C++ that...	54	Established	160	C++
15	zkmkarlsruhe/ofxTensorFlow2 TensorFlow 2 AI/ML library wrapper for openFrameworks	53	Established	119	C++
16	axonn-ai/axonn Parallel framework for training and fine-tuning deep neural networks	53	Established	72	Python
17	Neargye/hello_tf_c_api Neural Network TensorFlow C API	51	Established	474	C++
18	NiuTrans/NiuTensor NiuTensor is an open-source toolkit developed by a joint team from NLP Lab....	51	Established	385	C++
19	NervanaSystems/neon Intel® Nervana™ reference deep learning framework committed to best...	51	Established	3,869	Python
20	hpi-xnor/BMXNet (New version is out: https://github.com/hpi-xnor/BMXNet-v2) BMXNet: An...	50	Established	351	C++
21	PatWie/tensorflow-cmake TensorFlow examples in C, C++, Go and Python without bazel but with cmake...	50	Established	444	CMake
22	neo-ai/neo-ai-dlr Neo-AI-DLR is a common runtime for machine learning models compiled by AWS...	50	Established	496	C++
23	alibaba/BladeDISC BladeDISC is an end-to-end DynamIc Shape Compiler project for machine...	50	Established	919	C++
24	wy1iu/LargeMargin_Softmax_Loss Implementation for	50	Established	352	C++
25	tqchen/tinyflow Tutorial code on how to build your own Deep Learning System in 2k Lines	50	Established	2,016	C++
26	prabhuomkar/pytorch-cpp C++ Implementation of PyTorch Tutorials for Everyone	49	Emerging	2,129	C++
27	apache/tvm-vta Open, Modular, Deep Learning Accelerator	49	Emerging	333	Scala
28	apache/tvm-rfcs A home for the final text of all TVM RFCs.	48	Emerging	109	—
29	memoakten/ofxMSATensorFlow C++ openframeworks addon and examples integrating Google's TensorFlow...	48	Emerging	459	C++
30	Tiramisu-Compiler/tiramisu A polyhedral compiler for expressing fast and portable data parallel algorithms	48	Emerging	957	C++
31	MegEngine/MegEngine MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架	47	Emerging	4,808	C++
32	facebookresearch/TensorComprehensions A domain specific language to express machine learning workloads.	47	Emerging	1,765	C++
33	OpenMachine-ai/tinyfive TinyFive is a lightweight RISC-V emulator and assembler written in Python...	47	Emerging	71	Python
34	AngusG/tensorflow-xnor-bnn BinaryNets in TensorFlow with XNOR GEMM op	47	Emerging	154	C++
35	CEA-LIST/N2D2 N2D2 is an open source CAD framework for Deep Neural Network simulation and...	47	Emerging	158	C
36	mrphys/tensorflow-nufft Fast, Native Non-Uniform Fast Fourier Transform for TensorFlow	47	Emerging	24	C++
37	vlang/vtl The V Tensor Library	47	Emerging	160	V
38	apple/turicreate Turi Create simplifies the development of custom machine learning models.	46	Emerging	11,183	C++
39	nguyenphuminh/catniff Torch-like deep learning framework for Javascript	46	Emerging	8	TypeScript
40	neilcz/libGDL 一个移动端跨平台的gpu+cpu并行计算的cnn框架(A mobile-side cross-platform gpu+cpu parallel...	46	Emerging	92	C++
41	ducha-aiki/LSUVinit Reference caffe implementation of LSUV initialization	46	Emerging	114	C++
42	LISTENAI/thinker a lightweight deep learning framework for CSK60XX serial products	46	Emerging	25	C
43	jiazhihao/TASO The Tensor Algebra SuperOptimizer for Deep Learning	46	Emerging	740	C++
44	chochain/tensorForth Forth does tensors, in CUDA.	45	Emerging	56	C++
45	TensoriumCore/Tensorium_lib An early-stage HPC tensor and grid-kernel library for numerical relativity,...	45	Emerging	13	C++
46	hpi-xnor/BMXNet-v2 BMXNet 2: An Open-Source Binary Neural Network Implementation Based on MXNet	43	Emerging	232	C++
47	RubixML/Tensor A library and extension that provides objects for scientific computing in PHP.	43	Emerging	275	PHP
48	Infatoshi/batmobile High-performance CUDA kernels for equivariant graph neural networks (MACE,...	42	Emerging	43	Cuda
49	leggedrobotics/tensorflow-cpp Pre-built TensorFlow for C/C++ and CMake.	42	Emerging	117	Shell
50	tensil-ai/tensil Open source machine learning accelerators	41	Emerging	397	Scala
51	Pigrecos/TensorFlow.Delphi TensorFlow.Delphi (TF.Delphi) provides a Delphi(Pascal) Standard binding for...	41	Emerging	88	Pascal
52	google/minimalloc A lightweight memory allocator for hardware-accelerated machine learning	40	Emerging	180	C++
53	iree-org/iree-torch Torch Frontend for IREE	40	Emerging	25	Python
54	nict-wisdom/rannc RaNNC is an automatic parallelization middleware used to train very...	39	Emerging	57	C++
55	merrymercy/awesome-tensor-compilers A list of awesome compiler projects and papers for tensor computation and...	39	Emerging	2,734	—
56	skylook/tensorflow_cpp C and C++ examples for tensorflow	39	Emerging	128	C++
57	mgorshkov/np ⚡ NumPy-style arrays in C++ \| CUDA GPU + AVX512 CPU \| Tikhonov Regularized...	38	Emerging	10	C++
58	joennlae/halutmatmul Hashed Lookup Table based Matrix Multiplication (halutmatmul) - Stella Nera...	37	Emerging	216	Python
59	akielaries/openGPMP Hardware Accelerated General Purpose Mathematics Package (very stale)	35	Emerging	7	C++
60	marty1885/tiny-htm A tiny yet flexable framework for (HTM) Hierarchical Temporal Memory	35	Emerging	7	C++
61	jasmcaus/hazel A Tensor Library written in C++.	34	Emerging	5	C++
62	lucasdelimanogueira/PyNorch Recreating PyTorch from scratch (C/C++, CUDA, NCCL and Python, with...	34	Emerging	164	Python
63	explosion/thinc_gpu_ops 🔮 GPU kernels for Thinc	34	Emerging	9	C++
64	entropy-flux/Tannic A C++ Tensor Library	33	Emerging	3	C++
65	EECS-583-Group-24/ML-LOOP Using Machine Learning to Predict the Sequences of Optimization Passes in LLVM	33	Emerging	8	C
66	solomontesema/nn-weight-extractor Neural network weight extractor with batch normalization folding for...	33	Emerging	1	C++
67	Tamerkobba/Parallel-CNN This project explores the parallelization of Convolutional Neural Networks...	32	Emerging	5	C++
68	karimknaebel/itar tar file index for constant-time member access	32	Emerging	4	Python
69	Tensor-Array/Tensor-Array A C++ machine learning framework/library.	32	Emerging	2	C++
70	SanftMonster/megengine_cpp_training_example Examples for using MegEngine cpp API for model training, which support...	31	Emerging	2	C++
71	Accumulated/Accelerating-CNN-on-GPU-using-CUDA-C This repository is for implementing and accelerating CNN on GPU using NVIDIA...	31	Emerging	6	Jupyter Notebook
72	tensortask/ttp Tensor Transport Protocol (TTP)	31	Emerging	3	Go
73	YconquestY/Needle Imperative deep learning framework with customized GPU and CPU backend	31	Emerging	29	Python
74	trevorpogue/algebraic-nnhw Algebraic enhancements for GEMM & AI accelerators	30	Emerging	290	Python
75	vishnupsatish/microtensor Deep learning library (training & inference) and GPT-2 in C++ from scratch.	30	Emerging	36	C++
76	alarxx/Tensor-library Analogue to Math and ML libraries like numpy or pytorch	30	Emerging	6	C++
77	moritztng/cuda-ml Machine Learning Framework with Automatic Differentiation and Cuda...	29	Experimental	1	Cuda
78	Li-TianCheng/TinyDL 基于Eigen运算库的深度学习框架(支持CUDA加速)	29	Experimental	18	C++
79	Savernish/forgeNN forgeNN is a in-development purpose‑built neural network framework combining...	28	Experimental	2	Python
80	marcosalvalaggio/kiwigrad Mini deep learning framework written in Python C-API for Speed	28	Experimental	3	C
81	ianmkim/snnpp Spiking Neural Network implementation in pure C++ with minimal dependencies	27	Experimental	13	C++
82	Xeanos7913/Vensor A simple C++ machine learning library, using Vulkan for GPU acceleration.	27	Experimental	5	C++
83	Frobeniusnorm/Flint Tensor math framework for machine learning	26	Experimental	5	C++
84	EzraWolf/TinyMOA RISC-V CPU with an integrated SRAM-based compute-in-memory (CIM) accelerator...	25	Experimental	1	Python
85	albertopirillo/NITRO-D Novel framework for deep integer-only CNNs operating entirely in the...	25	Experimental	3	Jupyter Notebook
86	l1nkr/DL-Compiler-Navigation Machine Learning Compiler Road Map	25	Experimental	46	Jupyter Notebook
87	Gilberto-Galan/Mini-Framework-Deep-Learning-T-Tensor 🚀 Mini-Framework de Deep Learning desarrollado en C++/CUDA con bindings de...	24	Experimental	2	Cuda
88	rikhil-amonkar/pytorch-cpp-layernorm-accelerator Implemented a custom LayerNorm forward and backward pass extension in C++...	24	Experimental	1	C++
89	PedroHenriqueBatistaSilva/AdderNet Neural networks with zero multiplications at inference. AdderNet + HDC for...	23	Experimental	1	C
90	Amanda-Barbara/nvcaffe study nvcaffe code	23	Experimental	—	C++
91	Shengxiang-Lin/ParticleFlow-Lite This is an official implementation of "Lightweight Deep Learning Framework...	22	Experimental	16	C++
92	Sharveswar007/SSBLAST First open-source FP8 linear solver for consumer NVIDIA GPUs — 2-3x faster...	22	Experimental	—	Python
93	Nathanael007/8bit-cpu 🖥️ Design and simulate a custom 8-bit CPU with a 16-instruction ISA, 5-stage...	22	Experimental	—	Assembly
94	dbjwhs/inference-systems-lab C++17 inference platform: belief propagation, Mamba SSM, MoE, neuro-symbolic...	22	Experimental	—	C++
95	xusworld/tars Tars is a cool deep learning framework.	21	Experimental	1	C++
96	rizkysaputradev/Syntralinepp-Compiler SyntraLine++ is a compiler-based domain-specific language (DSL) for...	20	Experimental	1	C++
97	StxGuy/TenaciousTensors Fortran/C++ library for multidimensional algebra.	19	Experimental	4	C++
98	manili/ctorch CTorch is a super lightweight C implementation of PyTorch, built for...	18	Experimental	2	C
99	BlaiseMuhirwa/gladius An easy-to-use dynamic computation graph library for running e2e ML training.	18	Experimental	2	C++
100	saivishwak/DeepLearning_Compilers_Research DeepLearning Compilers Research	18	Experimental	2	—
101	DhruvSrikanth/CUDANN A distributed implementation of a deep learning framework in CUDA.	18	Experimental	2	C++
102	ColeAndrae/tensorgrad A high-performance deep learning framework written in C++, engineered from...	17	Experimental	1	Jupyter Notebook
103	Mobink980/Network-on-Chip As we transition into the era characterized by many-core architectures and...	17	Experimental	1	C++
104	Rishav-hub/GNetTrainer-package GNetTrainer is a Deep Learning web application for training and predicting...	17	Experimental	1	HTML
105	muditbhargava66/llvm-dl-optimizer LLVM-based Compiler Optimization for Deep Learning Kernels	17	Experimental	—	C++
106	rexionmars/ctorch A next library stb-style header-only library for Neural Networks	17	Experimental	1	C
107	rizukirr/ctorch Re-implement Pytorch in C	16	Experimental	1	C
108	hysmio/tensors-cpp Just a small repo intended for me to recreate a minimally working example of...	14	Experimental	—	C++
109	tmm-dl/tmm A hardware-agnostic, plugin-extensible CLI for training deep learning models...	14	Experimental	—	CMake
110	dhrvrc/Sparsity Native Similarity Searching for Dense & Sparse Vectors. Final Year Project....	14	Experimental	—	C++
111	Tanniefooted733/qemu-cpu-guide 🔍 Explore QEMU CPU models for KVM guests to enhance performance in...	14	Experimental	—	—
112	laluxx/tensors single header machine learning library	13	Experimental	—	C
113	soumik12345/libtorch-examples Basic Deep Learning examples using LibTorch C++ frontend	13	Experimental	9	C++
114	pgmesa/synapx A deep learning library powered by a C++ autograd engine, featuring a...	13	Experimental	—	C++
115	Naveen-Baburaj/Porting-PyTorch-to-LibTorch-Iris-Neural-Network-Implementation Porting a PyTorch neural network for Iris classification from Python to...	13	Experimental	—	C++
116	one-2/catalyst Educational ML framework exploring hardware-agnostic deep learning systems....	11	Experimental	—	C++
117	albertchristianto/night_fury Night Fury is a dragon that helps Hiccup achieves his dreams and the...	11	Experimental	—	C++
118	Samus1234/18-663-cpp-torch-from-scratch A C++ CPU and CUDA-GPU implementation of the deep-learning library - Torch...	11	Experimental	3	C++
119	claudio-bon/sparse-net In this project I have implemented the forward function of a Neural Network...	10	Experimental	2	C++
120	Xavier0301/BiM Code for distributed inference of WNN on the UPMEM PiM System	10	Experimental	2	Assembly

Comparisons in this category

ncnn and armnn (71 vs 61) ncnn and csi-nn2 (71 vs 56) tvm and tvm-ffi (75 vs 57)