yiliu30

yiliu30's Stars

• xai-org/grok-1

  Grok open release

  Language:Python49.6k5742108.3k

• karpathy/nanoGPT

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

  Language:Python37.5k3773186k

• facebookresearch/faiss

  A library for efficient similarity search and clustering of dense vectors.

  Language:C++31.6k4792.5k3.6k

• meta-llama/llama3

  The official Meta Llama 3 GitHub site

  Language:Python27.2k2262643.1k

• karpathy/llm.c

  LLM training in simple, raw C/CUDA

  Language:Cuda24.5k2461412.8k

• karpathy/nn-zero-to-hero

  Neural Networks: Zero to Hero

  Language:Jupyter Notebook11.9k287331.5k

• ai-boost/awesome-prompts

  Curated list of chatgpt prompts from the top-rated GPTs in the GPTs Store. Prompt Engineering, prompt attack & prompt protect. Advanced Prompt Engineering papers.

  5.3k638487

• pytorch/torchtune

  PyTorch native finetuning library

  Language:Python4.3k47720440

• openai/transformer-debugger

  Language:Python4k2514238

• ROCm/HIP

  HIP: C++ Heterogeneous-Compute Interface for Portability

  Language:C++3.8k142877539

• pytorch/executorch

  On-device AI across mobile, embedded and edge for PyTorch

  Language:C++2.2k60516367

• pytorch/ao

  PyTorch native quantization and sparsity for training and inference

  Language:Python1.6k41299177

• pytorch/functorch

  functorch is JAX-like composable function transforms for PyTorch.

  Language:Jupyter Notebook1.4k27522102

• huggingface/optimum-quanto

  A pytorch quantization backend for optimum

  Language:Python828813561

• OpenGVLab/OmniQuant

  [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

  Language:Python730168556

• SqueezeAILab/SqueezeLLM

  [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

  Language:Python649182743

• tspeterkim/flash-attention-minimal

  Flash Attention in ~100 lines of CUDA (forward pass only)

  Language:Cuda6304654

• IST-DASLab/marlin

  FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

  Language:Python626152948

• Vahe1994/SpQR

  Language:Python527192443

• google-research/sputnik

  A library of GPU kernels for sparse matrix operations.

  Language:C++24910850

• yxli2123/LoftQ

  Language:Python19943819

• Aaronhuang-778/BiLLM

  (ICML 2024) BiLLM: Pushing the Limit of Post-Training Quantization for LLMs

  Language:Python19761713

• puttsk/cuda-tutorial

  A set of hands-on tutorials for CUDA programming

  Language:Cuda1945333

• IST-DASLab/QUIK

  Repository for the QUIK project, enabling the use of 4bit kernels for generative inference - EMNLP 2024

  Language:C++1736712

• xijiu9/Train_Transformers_with_INT4

  Language:Python134534

• thu-nics/qllm-eval

  Code Repository of Evaluating Quantized Large Language Models

  Language:Python104554

• sunlex0717/DissectingTensorCores

  Language:Cuda793418

• iree-org/iree-torch

  Torch Frontend for IREE

  Language:Python25161111

• facebookexperimental/protoquant

  Prototype routines for GPU quantization written using PyTorch.

  Language:Python19908

• Quansight/torch-build

  Collection of scripts to build PyTorch and the domain libraries from source.

  Language:Shell8318