mcognetta

mcognetta's Stars

• tunib-ai/parallelformers

  Parallelformers: An Efficient Model Parallelization Toolkit for Deployment

  Language:Python77661

• mlcommons/algorithmic-efficiency

  MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvements in both training algorithms and models.

  Language:Python32262

• Liuhong99/Sophia

  The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”

  Language:Python93352

• cp-algorithms/cp-algorithms

  Algorithm and data structure articles for https://cp-algorithms.com (based on http://e-maxx.ru)

  Language:C++7.4k1.6k

• libprima/prima

  PRIMA is a package for solving general nonlinear optimization problems without using derivatives. It provides the reference implementation for Powell's derivative-free optimization methods, i.e., COBYLA, UOBYQA, NEWUOA, BOBYQA, and LINCOA. PRIMA means Reference Implementation for Powell's methods with Modernization and Amelioration, P for Powell.

  Language:Fortran30440

• IntelLabs/academic-budget-bert

  Repository containing code for "How to Train BERT with an Academic Budget" paper

  Language:Python30947

• e9t/nsmc

  Naver sentiment movie corpus

  Language:Python558211

• Tiiiger/QPyTorch

  Low Precision Arithmetic Simulation in PyTorch

  Language:Python26374

• bitsandbytes-foundation/bitsandbytes

  Accessible large language models via k-bit quantization for PyTorch.

  Language:Python6.1k611

• google-research/jaxpruner

  Language:Python20313

• triton-lang/triton

  Development repository for the Triton language and compiler

  Language:C++12.9k1.6k

• quantumaikr/KoreanLM

  한국어 언어모델 오픈소스

  Language:Python803

• JuliaSIMD/VectorizedRNG.jl

  Vectorized uniform and normal random samplers.

  Language:Julia337

• AshwinDeshpande96/Hierarchical-Softmax

  This is a scalable hierarchical softmax layer for Neural Networks with large output classes.

  Language:Jupyter Notebook194

• harrisonvanderbyl/rwkv-cpp-accelerated

  A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependencies

  Language:C++30619

• omlins/julia-gpu-course

  GPU Programming with Julia - course at the Swiss National Supercomputing Centre (CSCS), ETH Zurich

  Language:Jupyter Notebook24427

• openai/tiktoken

  tiktoken is a fast BPE tokeniser for use with OpenAI's models.

  Language:Python11.9k812

• SymbolicML/DynamicExpressions.jl

  Ridiculously fast symbolic expressions

  Language:Julia10315

• ggerganov/llama.cpp

  LLM inference in C/C++

  Language:C++65.7k9.4k

• kakaobrain/jejueo

  Jejueo Datasets for Machine Translation and Speech Synthesis

  Language:Python758

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python13.6k1.2k

• KanjiVG/kanjivg

  Kanji vector graphics

  Language:Python1.1k181

• sagemath/sage

  Main repository of SageMath

  Language:Python1.4k461

• karpathy/nanoGPT

  The simplest, fastest repository for training/finetuning medium-sized GPTs.

  Language:Python36.5k5.7k

• aojunzz/NM-sparsity

  Language:Python21229

• run-llama/llama_index

  LlamaIndex is a data framework for your LLM applications

  Language:Python35.8k5.1k

• tysam-code/hlb-CIFAR10

  Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)

  Language:Python1.2k75

• scandum/quadsort

  Quadsort is a branchless stable adaptive mergesort faster than quicksort.

  Language:C2.1k105

• BYVoid/OpenCC

  Conversion between Traditional and Simplified Chinese

  Language:C++8.4k975

• FluxML/FastAI.jl

  Repository of best practices for deep learning in Julia, inspired by fastai

  Language:Julia58751