Alternatives
Products that do what GitHub does
Differentiable sign/round/floor for PyTorch
- 1IS
2022 · github.com
- 2TL
Hello HN! For the past 6 months I've been working on an open source python library that implements differentiable geometric optics in PyTorch. It's very experimental still, but eventually the goal is to use it to design optical systems with a state of the art optimization framework and a beautiful code based API. Think OpenSCAD, but for optical systems. Not only is PyTorch's autograd an amazing general purpose optimizer, but torch.nn (the neural network building blocks) can be used pretty much out of the box to model an optical system. This is because there is a strong analogy to be made…
2025 · victorpoughon.github.io
- 3
- 4BG
Trying to do gradient descent using automatic differentiation over branchy programs? Or to combine them with neural networks for end-to-end training? Then this might be interesting to you. We develped DiscoGrad, a tool for automatic differentiation through C++ programs involving input-dependent control flow (e.g., "if (f(x) < c) { ... }", differentiating wrt. x) and randomness. Our initial motivation was to enable the use of gradient descent with simulations, which often rely heavily on such discrete branching. The latter makes plain autodiff mostly useless, since it can only account for the…
2024 · github.com
- 5LF
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
- 6
Save 30% of dev time - generate tests without writing code
2023
- 7GGradientMagic▲259
2020 · gradientmagic.com
- 8RT
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
- 9SC
2019 · github.com
- 10
- 11GA
All commands have the format `output = \func inputs` or just `\function inputs`. Points and scalars are built on the fly. Eg `\line a b` to an empty canvas creates points `a` and `b`, and joins them with a line. One can use broadcasting semantics similar to NumPy and PyTorch in a visual setting (imagine creating a list of circles where one dim corresponds to radius and another to the center). One can also use backpropagation, run gradient descent or visualize vector fields. Almost everything is reactive so changing a variable updates all of the downstream geometry. It also allows anyone to…
May 2026 · tinyvolt.com
- 12LO
Hi HN, I’m Joe. My friends Matthew, Jake and I are building Luminal (https://luminalai.com/), a GPU compiler for automatically generating fast GPU kernels for AI models. It uses search-based compilation to achieve high performance. We take high level model code, like you'd have in PyTorch, and generate very fast GPU code. We do that without using LLMs or AI - rather, we pose it as a search problem. Our compiler builds a search space, generates millions of possible kernels, and then searches through it to minimize runtime. You can try out a demo in `demos/matmul` on mac to…
2025 · github.com
- 13ZA
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
- 14SC
2021 · blog.tonari.no
- 15
- 16MM
2021 · everydayanchovies.github.io
- 17TT
I’ve been working on a project to bridge the gap between AI generation and my AxiDraw, and I think I finally have a workflow that avoids the usual headaches. If you’ve tried plotting AI-generated images, you probably know the struggle: generic tracing tools (like Potrace) trace the outline of a line, resulting in double-strokes that ruin the look and take twice as long to plot. What I tried previously: - Potrace / Inkscape Trace: Great for filled shapes, but results in "hollow" lines for line art. - Canny Edge Detection: Often too messy; it picks up noise and creates jittery paths. -…
Jan 2026 · github.com
- 18GT
Hi HN, In the past few years I've become more interested in machine learning. Since I'm sure the same is true for many here, I wanted to share this project I've been working on: glowstick uses type-directed metaprogramming to keep track of tensor shapes in Rust's type system and determine which operations are permitted or not at compile time. I find Rust has a lot of strengths when it comes to ML applications, but waiting until runtime to find shape related issues feels a bit strange since normally I don't run the code all that often while developing. Given Rust has fancy types available, I…
2025 · github.com
- 19RC
2021 · github.com
- 20PP
2025 · github.com
- 21AI
(space = reset) Fluid mechanics is an extremely interesting topic and I have been creative coding for a couple of months now. Therefore I started working on flow fields in processing. It had so much fun playing around with the different parameters in this project, I decided to rewrite in p5.js an added a control panel. You can change most of the parameters (within some constraints I thought to be reasonable), randomize the values and export and import settings. Hopefully some coders here get inspired and also join the great creative coding community.
2024 · synapse.nugatio.com
- 22PC
pyCirclize is a circular visualization python package implemented based on matplotlib. This package was developed for the purpose of easily and beautifully plotting circular figure such as Circos Plot and Chord Diagram in Python. I'd love to hear your feedback. Document: https://moshi4.github.io/pyCirclize/
2023 · github.com
- 23CT
2023 · github.com
- 24TT
2020 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →