qinsiyuan-cool

qinsiyuan-cool's Stars

• inside-compiler/llvm-project

  The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

  7

• inside-compiler/Inside-LLVM-Code-Gen

  图书《深入理解LLVM代码生成》的配套示例代码

  Language:LLVM15

• 0voice/introduce_c-cpp_manual

  一个收集C/C++新手学习的入门项目，整理收纳开发者开源的小项目、工具、框架、游戏等，视频，书籍，面试题/算法题，技术文章。

  Language:C++6k770

• LearningInfiniTensor/TinyInfiniTensor

  Language:C++661

• hahnyuan/LLM-Viewer

  Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline model in a user-friendly interface.

  Language:Python35944

• liguodongiot/llm-action

  本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

  Language:HTML12.5k1.3k

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python14.9k1.4k

• AdvancedCompiler/AdvancedCompiler

  先进编译实验室的个人主页

  Language:C++343

• 0voice/interview_internal_reference

  2023年最新总结，阿里，腾讯，百度，美团，头条等技术面试题目，以及答案，专家出题人分析汇总。

  Language:Python36.7k9.4k

• ModelTC/lightllm

  LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

  Language:Python2.7k217

• 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:Cuda32668

• THU-DSP-LAB/llvm-project

  LLVM OpenCL C compiler suite for ventus GPGPU

  Language:C++3816

• SqueezeAILab/LLMCompiler

  [ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

  Language:Python1.6k116

• zjin-lcf/HeCBench

  Language:C++22680

• ai-dawang/PlugNPlay-Modules

  Language:Python2.8k236

• hustvl/Vim

  [ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

  Language:Python3.1k208

• NVlabs/instant-ngp

  Instant neural graphics primitives: lightning fast NeRF and more

  Language:Cuda16.2k1.9k

• microsoft/BitBLAS

  BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

  Language:Python48234

• microsoft/T-MAC

  Low-bit LLM inference on CPU with lookup table

  Language:C++63348

• karpathy/nano-llama31

  nanoGPT style version of Llama 3.1

  Language:Python1.3k67

• zjhellofss/KuiperInfer

  校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step

  Language:C++2.6k302

• DefTruth/Awesome-LLM-Inference

  📖A curated list of Awesome LLM/VLM Inference Papers with codes, such as FlashAttention, PagedAttention, Parallelism, etc. 🎉🎉

  3.1k211

• zjhellofss/KuiperLLama

  校招、秋招、春招、实习好项目，带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。

  Language:C++25660

• openmlsys/openmlsys-cuda

  Tutorials for writing high-performance GPU operators in AI frameworks.

  Language:Cuda12616

• InfiniTensor/InfiniTensor

  Language:C++18030

• wangzhaode/llm-export

  llm-export can export llm model to onnx.

  Language:Python25530

• HeKun-NVIDIA/CUDA-Programming-Guide-in-Chinese

  This is a Chinese translation of the CUDA programming guide

  1.4k218

• karpathy/llm.c

  LLM training in simple, raw C/CUDA

  Language:Cuda24.9k2.8k

• 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:Cuda878138

• Cjkkkk/CUDA_gemm

  A simple high performance CUDA GEMM implementation.

  Language:Cuda34137