tangpanyu

tangpanyu's Stars

• ggerganov/llama.cpp

  LLM inference in C/C++

  Language:C++74.3k5714.5k10.7k

• RVC-Boss/GPT-SoVITS

  1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

  Language:Python43k2351.6k4.8k

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python16.5k1241.3k1.6k

• triton-lang/triton

  Development repository for the Triton language and compiler

  Language:MLIR15k1961.7k1.9k

• facebookresearch/sam2

  The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

  Language:Jupyter Notebook14.7k824911.6k

• davisking/dlib

  A toolkit for making real world machine learning and data analysis applications in C++

  Language:C++13.9k4792.2k3.4k

• rui314/chibicc

  A small C compiler

  Language:C10k173115911

• DA-southampton/NLP_ability

  总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力

  Language:Python7.2k10651.2k

• NVIDIA/cuda-samples

  Samples for CUDA Developers which demonstrates features in CUDA Toolkit

  Language:C7.2k1182632k

• DefTruth/CUDA-Learn-Notes

  📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).

  Language:Cuda3k2220308

• flashinfer-ai/flashinfer

  FlashInfer: Kernel Library for LLM Serving

  Language:Cuda2.5k27241258

• CodingHanYa/workspace

  workspace是基于C++11的轻量级异步执行框架，支持：通用任务异步并发执行、优先级任务调度、自适应动态线程池、高效静态线程池、异常处理机制等。

  Language:C++1.1k833168

• Liu-xiandong/How_to_optimize_in_GPU

  This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.

  Language:Cuda9631316150

• kaitoukito/Computer-Science-Textbooks

  Collect some CS textbooks for learning.

  906140250

• mst272/LLM-Dojo

  欢迎来到 LLM-Dojo，这里是一个开源大模型学习场所，使用简洁且易阅读的代码构建模型训练框架(支持各种主流模型如Qwen、Llama、GLM等等)、RLHF框架(DPO/CPO/KTO/PPO)等各种功能。👩‍🎓👨‍🎓

  Language:Python62422758

• zeux/calm

  CUDA/Metal accelerated language model inference

  Language:C52913023

• Bruce-Lee-LY/cuda_hgemm

  Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruction.

  Language:Cuda36851474

• Cjkkkk/CUDA_gemm

  A simple high performance CUDA GEMM implementation.

  Language:Cuda3534340

• KnowingNothing/MatmulTutorial

  A Easy-to-understand TensorOp Matmul Tutorial

  Language:C++331101238

• 66RING/tiny-flash-attention

  flash attention tutorial written in python, triton, cuda, cutlass

  Language:Cuda30531232

• gavinliu6/Makefile-Tutorial-zh-CN

  Makefile 教程

  Language:HTML2815231

• parallel101/stl1weekend

  Build your own STL in one weekend

  Language:C++26841020

• TiledTensor/TiledCUDA

  We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.

  Language:C++17936411

• AyakaGEMM/Hands-on-GEMM

  Language:Cuda1132416

• reed-lau/cute-gemm

  Language:C++1072532

• BooHwang/segment_anything_tensorrt

  Accelerate segment anything model inference using Tensorrt 8.6.1.6

  Language:Python87267

• NVIDIA/online-softmax

  Benchmark code for the "Online normalizer calculation for softmax" paper

  Language:Cuda85507

• ankan-ban/llama_cu_awq

  llama INT4 cuda inference with AWQ

  Language:C++51396

• ankan-ban/llama2.cu

  Inference Llama 2 in one file of pure Cuda

  Language:Python17212

• Tongkaio/MoE_inference

  CUDA MoE kernels.

  Language:Cuda30