Pinned Repositories
Competitive-Coding-Benchmark
Benchmark LLMs against a set of high quality representative competitive coding problems sourced from cses.fi
CoPE-cuda
Contextual Position Encoding but with some custom CUDA Kernels https://arxiv.org/abs/2405.18719
cudatiger
An accelerated implementation of the Tiger optimizer for PyTorch, supercharged with Triton for enhanced CUDA GPU efficiency. More Memory efficient than Adam. https://kexue.fm/archives/9512
llama2.jl
Inference Llama 2 in one file of pure C. Nahh wait, now fresh in Julia!
self-compressing-nn-jax
Implementation of Self-Compressing Neural Networks in JAX https://arxiv.org/pdf/2301.13142 ported from tinygrad https://github.com/geohot/ai-notebooks/blob/master/mnist_self_compression.ipynb
tinyfep
A simplified and abstracted rendition of FEP+ (Free Energy Perturbation) for molecular simulations. https://www.schrodinger.com/products/fep
juvi21's Repositories
juvi21/llama2.jl
Inference Llama 2 in one file of pure C. Nahh wait, now fresh in Julia!
juvi21/CoPE-cuda
Contextual Position Encoding but with some custom CUDA Kernels https://arxiv.org/abs/2405.18719
juvi21/Competitive-Coding-Benchmark
Benchmark LLMs against a set of high quality representative competitive coding problems sourced from cses.fi
juvi21/cudatiger
An accelerated implementation of the Tiger optimizer for PyTorch, supercharged with Triton for enhanced CUDA GPU efficiency. More Memory efficient than Adam. https://kexue.fm/archives/9512
juvi21/tinyfep
A simplified and abstracted rendition of FEP+ (Free Energy Perturbation) for molecular simulations. https://www.schrodinger.com/products/fep
juvi21/bittensor
Internet-scale Neural Networks
juvi21/GPU-Puzzles-Solutions-speedrun-twitch
Solutions for all srushs CUDA GPU-Puzzles utilizing numba. Speedrun for twitch.
juvi21/guess-the-prompt
Guess the prompt Arena
juvi21/juvi21
juvi21/kernel42.ai
Landing page for kernel42.ai in React Typescript
juvi21/leanmathproofs
various math proofs for fun me trying out lean and I consider worth sharing
juvi21/nngdb
An terminal based interpretability Tool that feels like gdb
juvi21/self-compressing-nn-jax
Implementation of Self-Compressing Neural Networks in JAX https://arxiv.org/pdf/2301.13142 ported from tinygrad https://github.com/geohot/ai-notebooks/blob/master/mnist_self_compression.ipynb
juvi21/cuda-Wavelet-KAN
CUDA implementation of Wavelet KAN.
juvi21/efficient-kan
An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).
juvi21/llama3.1-syn-code
juvi21/mistral-common
juvi21/Open-Reasoning-Tasks
A comprehensive repository of reasoning tasks for LLMs (and beyond)
juvi21/quanto
A pytorch Quantization Toolkit
juvi21/ShallowSpeed
Small scale distributed training of sequential deep learning models, built on Numpy and MPI.
juvi21/tinygrad
You like pytorch? You like micrograd? You love tinygrad! ❤️
juvi21/useful-slurm-scripts
Useful Slurm Scripts to make my life easier
juvi21/WARP-pytorch
Pytorch implementation of: https://arxiv.org/pdf/2406.16768v1
juvi21/yet-another-applied-llm-benchmark
A benchmark to evaluate language models on questions I've previously asked them to solve.