MARD1NO

MARD1NO's Stars

• QwenLM/qwen.cpp

  C++ implementation of Qwen-LM

  Language:C++48939

• apple/ml-ferret

  Language:Python7.9k463

• RulinShao/LightSeq

  Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers

  Language:Python1557

• pytorch/torchdistx

  Torch Distributed Experimental

  Language:Python11331

• Oneflow-Inc/faster-chatglm-6b

  Language:Python6

• mit-han-lab/streaming-llm

  [ICLR 2024] Efficient Streaming Language Models with Attention Sinks

  Language:Python6.3k354

• SkunkworksAI/hydra-moe

  Language:Python40315

• dlsyscourse/hw2

  Language:Python39

• AlibabaResearch/flash-llm

  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity

  Language:Cuda14911

• facebookresearch/fairseq2

  FAIR Sequence Modeling Toolkit 2

  Language:Python59255

• krahets/hello-algo

  《Hello 算法》：动画图解、一键运行的数据结构与算法教程。支持 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 代码。简体版和繁体版同步更新，English version ongoing

  Language:Java76.9k9.7k

• huawei-noah/Efficient-Computing

  Efficient computing methods developed by Huawei Noah's Ark Lab

  Language:Jupyter Notebook1.1k198

• Mellanox/nccl-rdma-sharp-plugins

  RDMA and SHARP plugins for nccl library

  Language:C14128

• mlc-ai/mlc-ai.github.io

  Language:HTML51

• Azure/msccl-executor-nccl

  Language:C++246

• minitorch/quizzes

  Class quizzes for minitorch and an auto-grader.

  Language:Python1

• irfanICMLL/structure_knowledge_distillation

  The official code for the paper 'Structured Knowledge Distillation for Semantic Segmentation'. (CVPR 2019 ORAL) and extension to other tasks.

  Language:Python689103

• leptonai/leptonai

  A Pythonic framework to simplify AI service building

  Language:Python2.5k159

• punica-ai/punica

  Serving multiple LoRA finetuned LLM as one

  Language:Python85638

• ziplab/efficient-stable-diffusion

  16

• TIGER-AI-Lab/MAmmoTH

  Code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning" (ICLR 2024)

  Language:Jupyter Notebook28538

• THUDM/MathGLM

  Official Pytorch Implementation for MathGLM

  Language:Python31325

• FasterDecoding/Medusa

  Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

  Language:Jupyter Notebook1.9k125

• getgridea/gridea

  ✍️ A static blog writing client (一个静态博客写作客户端)

  Language:TypeScript9.9k791

• wjakob/nanobind

  nanobind: tiny and efficient C++/Python bindings

  Language:C++2.1k153

• baichuan-inc/Baichuan2

  A series of large language models developed by Baichuan Intelligent Technology

  Language:Python4k278

• bojone/bytepiece

  更纯粹、更高压缩率的Tokenizer

  Language:Python40818

• openppl-public/ppl.llm.kernel.cuda

  Language:C++11824

• softmax1/Flash-Attention-Softmax-N

  CUDA and Triton implementations of Flash Attention with SoftmaxN.

  Language:Python645

• yester31/Cutlass_EX

  study of cutlass

  Language:Cuda174