AI · alternatives · 2026
24 alternatives to Pytorch_block_sparse: smaller, faster neural networks
Today I am excited to release pytorch-block-sparse: a *drop-in* replacement of @PyTorch Linear with GPU-efficient sparsity: 75% sparsity➡️4x less memory + 2x the speed! Code & tutorials to use to train your own sparse models: https://t.co/HMO11zWAjk
Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes. Pytorch_block_sparse: smaller, faster neural networks launched in 2020; newer entries below may have overtaken it.
- 1
min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch - kuprel/min-dalle
2022 · github.com · its alternatives →
- 2
I ported Microsoft's TRELLIS.2 (4B parameter image-to-3D model) to run on Apple Silicon via PyTorch MPS. The original requires CUDA with flash_attn, nvdiffrast, and custom sparse convolution kernels: none of which work on Mac. I replaced the CUDA-specific ops with pure-PyTorch alternatives: a gather-scatter sparse 3D convolution, SDPA attention for sparse transformers, and a Python-based mesh extraction replacing CUDA hashmap operations. Total changes are a few hundred lines across 9 files. Generates ~400K vertex meshes from single photos in about 3.5 minutes on M4 Pro (24GB). Not as fast as…
Apr 2026 · github.com · its alternatives →
- 3
Hello HN, We are pleased to introduce you graphlearn-for-pytorch (https://github.com/alibaba/graphlearn-for-pytorch), an open-source distributed graph neural network library based on PyTorch and compatible with PyG. Our library is designed to make it easy for developers to build and train large-scale graph models in a distributed environment. With graphlearn-for-pytorch, you can leverage GPUs to accelerate graph sampling and utilize UVA to reduce the overheads of feature collection. Following a scalable design, graphlearn-for-pytorch supports training GNN models on…
2023 · github.com · its alternatives →
- 4
Fresh and (I think) clean implementations of Faster R-CNN in PyTorch and TensorFlow 2/Keras. I wanted to learn about object detectors and decided to understand and implement a foundational model in the field, Faster R-CNN (elements of which are still used in modern models to this day), using the paper alone. That proved to be more difficult than expected and I had to relent and take a peak at existing implementations to fill in some important gaps. I've documented my struggles and learnings in the README for others to benefit from. I also wanted to solidify my understanding of…
2022 · github.com · its alternatives →
- 5
- 6
We're excited to announce that we've open-sourced LeanRL, a lightweight PyTorch reinforcement learning library that provides recipes for fast RL training using torch.compile and CUDA graphs. By leveraging these tools, we've achieved significant speed-ups compared to the original CleanRL implementations - up to 6x faster! Reinforcement learning is notoriously CPU-bound due to the high frequency of small CPU operations. PyTorch's powerful compiler can help alleviate these issues, but comes with its own costs. LeanRL addresses this challenge by providing simple recipes to accelerate your…
2024 · github.com · its alternatives →
- 7
Forge Agent▲113Swarm Agents That Turn Slow PyTorch Into Fast GPU Kernels
Jan 2026 · rightnowai.co · its alternatives →
- 8
Pytorch script hot swap: Change code without unloading your LLM from VRAM - valine/training-hot-swap
2025 · github.com · its alternatives →
- 9
- 10
Open-source machine learning library by Google
2018 · tensorflow.org · its alternatives →
- 11
A minimalist deep learning library written from scratch in Python - sradc/SmallPebble
2021 · github.com · its alternatives →
- 12
This is a low-level opensource library I developed for my own use and decided to share, as it makes it possible to process large checkpoints of neural networks without renting high-RAM instances, on a regular PC. It replaces torch.load() with a custom function that produces a dictionary that materializes tensors on the fly. Compared to other solutions it doesn't require sharding or re-encoding checkpoints and uses them completely as-is. It is a foundation to make it possible to run inference and compress language models and other large models one layer at a time - in principle, even one…
2023 · github.com · its alternatives →
- 13
Perform data science on data that remains in someone else's server - OpenMined/PySyft
2018 · github.com · its alternatives →
- 14
- 15
Research Framework for easy and efficient training of GANs based on Pytorch - torchgan/torchgan
2018 · github.com · its alternatives →
- 16
To get benefits from sparsity, you usually need to have very sparse matrices, impose some structure on the sparsity pattern or have specialized hardware. None of it is the case if you want to rune pruned LLMs on consumer devices. I wanted to see how far can you push it on a GPU and ended up with this. Blog: https://www.grizzlytech.dev/blog/macko-spmv Paper: https://arxiv.org/abs/2511.13061 Code (example with torch): https://github.com/vlejd/macko_spmv
Nov 2025 · github.com · its alternatives →
- 17
A simple re-implementation of Google's sparsehash as a learning excercise. - qpfiffer/Simple-Sparsehash
2015 · github.com · its alternatives →
- 18
- 19
Minimal, readable LLM post-training experiments on one 8GB GPU. Measures forgetting, seed variance, and RL emergence. - pochenai/nano-llm-posttraining
Aug 2026 · github.com · its alternatives →
- 20
2024 · gitlab.com · its alternatives →
- 21
Official PyTorch implementation of NeuroFlow: EMA-Gated Temporal Sequence Compression for Vision Transformers. Achieves up to 55.8x wall-clock speedup for video inference via semantic surprise routing and a training-free Dual-Memory Reconstruction Protocol. - ynnk-research/-NeuroFlow
May 2026 · github.com · its alternatives →
- 22
Update as of November 18, 2021: The version of PySyft mentioned in this post has been deprecated. Any implementations using this older version of PySyft are…
2019 · blog.openmined.org · its alternatives →
- 23IC
I spent the past week implementing a 1 Layer Neural Net and training it on MNIST within the visual scripting language provided by scratch.mit.edu. It was tedious, but ultimately not too difficult. The code runs incredibly slowly, so much so that 64 samples of MNIST takes 5+ hours to train on my machine. There were a lot of little mini challenges that were fun to overcome (implementing softmax was very tricky). If you're interested, I encourage you to try and improve on it! More details in the linked blog post.
2024 · bell-boy.github.io · its alternatives →
- 24
BlockDL▲12Hi everyone. Designing neural network architectures is inherently a visual process. Every time I train a new model, I find myself sketching it out on paper before translating it into code (and still running into shape mismatches no matter how many networks I've built). So I built BlockDL: a free and open-source tool to design neural networks visually in your browser. It updates live Python/Keras code as you build, and automatically checks for shape and connectivity errors in real time. It supports: - Most common layer types (Conv2D, Dense, LSTM, etc.) - Multiple input/output…
2025 · blockdl.com · its alternatives →
Also compare
- I stripped DALL·E Mini to its bare essentials and converted it to Torch alternatives
- Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon alternatives
- Graphlearn-for-PyTorch, distributed graph learning on PyTorch alternatives
- Faster R-CNN object detector implemented in PyTorch and TensorFlow 2 alternatives
- TensorFire alternatives
- LeanRL: Fast PyTorch RL with Torch.compile and CUDA Graphs alternatives
Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →