pinxuezhao

pinxuezhao's Stars

• karpathy/nanoGPT

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

  Language:Python36.2k3673155.7k

• vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Language:Python26.8k2244.4k3.9k

• unslothai/unsloth

  Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

  Language:Python15.6k1028021k

• OpenBMB/MiniCPM-V

  MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

  Language:Python11.9k101511836

• NVIDIA/NeMo

  A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

  Language:Python11.5k2012.2k2.4k

• mistralai/mistral-inference

  Official inference library for Mistral models

  Language:Jupyter Notebook9.5k122136841

• THUDM/CogVideo

  Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

  Language:Python7.2k115219666

• srush/GPU-Puzzles

  Solve puzzles. Learn CUDA.

  Language:Jupyter Notebook5.7k2930335

• allenai/OLMo

  Modeling, training, eval, and inference code for OLMo

  Language:Python4.4k45189436

• linkedin/Liger-Kernel

  Efficient Triton Kernels for LLM Training

  Language:Python2.9k3571144

• johnma2006/mamba-minimal

  Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

  Language:Python2.5k2427185

• minitorch/minitorch

  The full minitorch student suite.

  Language:Python1.8k185351

• microsoft/DeepSpeed-MII

  MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

  Language:Python1.8k41295173

• xdit-project/xDiT

  xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) on multi-GPU Clusters

  Language:Python47846840

• NVIDIA/cuCollections

  Language:C++4641718284

• srush/annotated-mamba

  Annotated version of the Mamba paper

  Language:Jupyter Notebook44522317

• harvardnlp/namedtensor

  Named Tensor implementation for Torch

  Language:Jupyter Notebook441223142

• Dao-AILab/causal-conv1d

  Causal depthwise conv1d in CUDA, with a PyTorch interface

  Language:Cuda28241954

• microsoft/mscclpp

  MSCCL++: A GPU-driven communication stack for scalable AI applications

  Language:C++233198630

• microsoft/sarathi-serve

  A low-latency & high-throughput serving engine for LLMs

  Language:Python17251725

• llm-random/llm-random

  Language:Python16891212

• SamGinzburg/VectorVisor

  VectorVisor is a vectorizing binary translator for GPUs, designed to make it easy to run many copies of a single-threaded WebAssembly program in parallel using GPUs

  Language:WebAssembly142553

• netx-repo/PipeSwitch

  PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications

  Language:Python1245633

• byungsoo-oh/ml-systems-papers

  Curated collection of papers in machine learning systems

  123507

• tommyip/mamba2-minimal

  Minimal Mamba-2 implementation in PyTorch

  Language:Python88219

• parasailteam/coconet

  Language:HTML724911

• kamalkraj/minGPT-TF

  A minimal TF2 re-implementation of the OpenAI GPT training

  Language:Jupyter Notebook553218

• gpgpu-sim/pytorch-gpgpu-sim

  Modified version of PyTorch able to work with changes to GPGPU-Sim

  Language:C++444824

• SJTU-IPADS/ugache

  Language:C++20924

• MINI-PYTORCH/MINI-TORCH

  Mini-pytorch implemented from scratch using Python

  Language:Python90