miniF2F
tinycudann
miniF2F  tinycudann  

4  9  
262  3,468  
3.9%  3.8%  
0.0  5.9  
10 months ago  7 days ago  
ObjectiveC++  C++  
  GNU General Public License v3.0 or later 
Stars  the number of stars that a project has on GitHub. Growth  month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
miniF2F

[D] Have their been any attempts to create a programming language specifically for machine learning?
That said, you *can* write down a desired type and have a system write down a ton of type annotations or generate a bunch of code to prove that the type you wrote down is satisfied by your program. There's been recent work on this in deep learning for theorem proving, such as this work which uses GPT for proving theorems in Lean, a dependently type programming language and theorem prover. A better approach though would be to combine this with an actual tree search algorithm to allow a more structured search over the space of proofs, instead of trying to generate full correct proofs in one shot. Hypertree Proof Search does this, using a variant of AlphaZero to search and finetune the neural net. Unfortunately it hasn't been opensourced though, and it's pretty compute intensive, so we can't use this for actual type inference yet. But yeah there's active interest in doing this kind of thing, both as a proving ground for using RL for reasoning tasks and from mathematicians for theoremproving.
 [D] First Author Interview: AI & formal math (Formal Mathematics Statement Curriculum Learning)
 [D] OpenAI tackles Math  Formal Mathematics Statement Curriculum Learning (Paper Explained Video)
 MiniF2F
tinycudann

[D] Have their been any attempts to create a programming language specifically for machine learning?
In the opposite direction from your question is a very interesting project, TinyNN all implemented as close to the metal as possible and very fast: https://github.com/NVlabs/tinycudann

A CUDAfree instant NGP renderer written entirely in Python: Support realtime rendering and camera interaction and consume less than 1GB of VRAM
This repo only implemented the rendering part of the NGP but is more simple and has a lesser amount of code compared to the original (InstantNGP and tinycudann).
 Tiny CUDA Neural Networks: fast C++/CUDA neural network framework
 Making 3D holograms this weekend with the very “Instant” Neural Graphics Primitives by nvidia — made this volume from 100 photos taken with an old iPhone 7 Plus
 NVlabs/tinyCUDAnn: fast C++/CUDA neural network framework

Small Neural networks in Julia 5x faster than PyTorch
...a C++ library with a CUDA backend. But these highperformance building blocks might only be saturating the GPU fully if the data is large enough.
I haven't looked at implementing these things, but I imagine uf you have smaller networks and thus less data, the large building blocks may not be optimal. You may for example want to fuse some operations to reduce memory latency from repeated memory access.
In PyTorch world, there are approaches for small networks as well, there is https://github.com/NVlabs/tinycudann  as far as I understand from the first link in the README, it makes clever use of the CUDA shared memory, which can hold all the weights of a tiny network (but not larger ones).
 [R] Instant Neural Graphics Primitives with a Multiresolution Hash Encoding (Training a NeRF takes 5 seconds!)
 Tiny CUDA Neural Networks
 RealTime Neural Radiance Caching for Path Tracing
What are some alternatives?
tensor_annotations  Annotating tensor shapes using Python types
instantngp  Instant neural graphics primitives: lightning fast NeRF and more
einops  Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
blis  BLASlike Library Instantiation Software Framework
torchtyping  Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.
diffrax  Numerical differential equation solvers in JAX. Autodifferentiable and GPUcapable. https://docs.kidger.site/diffrax/
FL  FL language specification and reference implementations
juliaup  Julia installer and version multiplexer
dexlang  Research language for array processing in the Haskell/ML family
RecursiveFactorization
jaxtyping  Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/
RecursiveFactorization.jl