Alternatives and similar repositories for AI-Infer-Engine-From-Zero:

Users that are interested in AI-Infer-Engine-From-Zero are comparing it to the libraries listed below

• MegEngine / MegCC
  MegCC是一个运行时超轻量，高效，移植简单的深度学习模型编译器
  ☆476Updated 4 months ago
• Oldpan / DeployIsAllYouNeed
  ☆120Updated last year
• Eddie-Wang1120 / Professional-CUDA-C-Programming-Code-and-Notes
  CUDA C 编程权威指南代码实现 包含了书上第二章到第八章的大部分代码实现和作者笔记，全由作者本人手动实现，难免有错误的地方，请大家谨慎参考，非常欢迎对错误的指正。 如果有帮助的话请Star一下，对作者帮助很大，谢谢！
  ☆319Updated 2 years ago
• mlc-ai / mlc-zh
  ☆600Updated 8 months ago
• dingyuqing05 / trt2022_wenet
  ☆71Updated 2 years ago
• scarsty / ncnn-editor
  ncnn和pnnx格式编辑器
  ☆130Updated 4 months ago
• openmlsys / openmlsys-cuda
  Tutorials for writing high-performance GPU operators in AI frameworks.
  ☆129Updated last year
• BBuf / how-to-learn-deep-learning-framework
  how to learn PyTorch and OneFlow
  ☆395Updated 11 months ago
• torchpipe / torchpipe
  Serving Inside Pytorch
  ☆155Updated this week
• Tongkaio / CUDA_Kernel_Samples
  CUDA 算子手撕与面试指南
  ☆174Updated last month
• nndeploy / nndeploy
  nndeploy is an end-to-end model inference and deployment framework. It aims to provide users with a powerful, easy-to-use, high-performan…
  ☆701Updated this week
• ifromeast / cuda_learning
  learning how CUDA works
  ☆208Updated this week
• AyakaGEMM / Hands-on-GEMM
  ☆111Updated 11 months ago
• MegEngine / mperf
  mperf是一个面向移动/嵌入式平台的算子性能调优工具箱
  ☆178Updated last year
• BBuf / onnx_learn
  ☆97Updated 3 years ago
• YellowOldOdd / SDBI
  Simple Dynamic Batching Inference
  ☆145Updated 2 years ago
• BBuf / how-to-optimize-gemm
  ☆95Updated 3 years ago
• zjhellofss / KuiperCourse
  b站上的课程
  ☆71Updated last year
• PaddleJitLab / CUDATutorial
  A self-learning tutorail for CUDA High Performance Programing.
  ☆398Updated 2 months ago
• harleyszhang / lite_llama
  A light llama-like llm inference framework based on the triton kernel.
  ☆94Updated last week
• wangzhaode / llm-export
  llm-export can export llm model to onnx.
  ☆267Updated last month
• PaddlePaddle / CINN
  Compiler Infrastructure for Neural Networks
  ☆145Updated last year
• PaddlePaddle / PaddleCustomDevice
  PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)
  ☆81Updated this week
• HeKun-NVIDIA / TensorRT-Developer_Guide_in_Chinese
  ☆262Updated 2 years ago
• pigirons / sgemm_hsw
  This is an implementation of sgemm_kernel on L1d cache.
  ☆223Updated last year
• MegEngine / MegPeak
  ☆243Updated last year
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆79Updated last month
• OpenPPL / ppl.nn.llm
  ☆139Updated 10 months ago
• OpenPPL / ppl.llm.serving
  ☆127Updated 2 months ago
• bytedance / ByteTransformer
  optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
  ☆469Updated 11 months ago