kumarkrishna's Stars
EleutherAI/pythia
The hub for EleutherAI's work on interpretability and learning dynamics
sirupsen/napkin-math
Techniques and numbers for estimating system's performance from first-principles
ml-explore/mlx
MLX: An array framework for Apple silicon
facebookresearch/deit
Official DeiT repository
apple/axlearn
An Extensible Deep Learning Library
srush/llama2.rs
A fast llama2 decoder in pure Rust.
srush/GPU-Puzzles
Solve puzzles. Learn CUDA.
swansonk14/p_tqdm
Parallel processing with progress bars
facebookresearch/ConvNeXt-V2
Code release for ConvNeXt V2 model
lucidrains/perceiver-pytorch
Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch
JonasGeiping/cramming
Cramming the training of a (BERT-type) language model into limited compute.
facebookresearch/xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.
facebookresearch/mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
facebookresearch/iopath
A python library that provides common I/O interface across different storage backends.
NVIDIA/enroot
A simple yet powerful tool to turn traditional container/OS images into unprivileged sandboxes.
NVIDIA/apex
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
arogozhnikov/einops
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
facebookresearch/faiss
A library for efficient similarity search and clustering of dense vectors.
facebookresearch/vissl
VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
open-mmlab/mmselfsup
OpenMMLab Self-Supervised Learning Toolbox and Benchmark
google-deepmind/deepmind-research
This repository contains implementations and illustrative code to accompany DeepMind publications
Dao-AILab/flash-attention
Fast and memory-efficient exact attention
triton-lang/triton
Development repository for the Triton language and compiler
pydicom/pydicom
Read, modify and write DICOM files with python code
facebookresearch/shumai
Fast Differentiable Tensor Library in JavaScript and TypeScript with Bun + Flashlight
google/praxis
microsoft/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
tensorflow/tpu
Reference models and tools for Cloud TPUs.
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
google-deepmind/jmp
JMP is a Mixed Precision library for JAX.