Alternatives and similar repositories for community:

Users that are interested in community are comparing it to the libraries listed below

• PaddlePaddle / PaddleCustomDevice
  PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)
  ☆80Updated this week
• PaddlePaddle / CINN
  Compiler Infrastructure for Neural Networks
  ☆145Updated last year
• PaddlePaddle / docs
  Documentations for PaddlePaddle
  ☆247Updated last week
• PaddlePaddle / benchmark
  ☆78Updated 2 weeks ago
• PaddlePaddle / Paddle-Inference-Demo
  ☆247Updated last month
• PaddlePaddle / PaddleTest
  PaddlePaddle TestSuite
  ☆44Updated this week
• PaddlePaddle / PaDiff
  Paddle Automatically Diff Precision Toolkits.
  ☆49Updated 10 months ago
• AyakaGEMM / Hands-on-GEMM
  ☆110Updated 11 months ago
• PaddlePaddle / PaConvert
  PaddlePaddle Code Convert Toolkit. 『飞桨』深度学习代码转换工具
  ☆95Updated this week
• OpenPPL / ppl.pmx
  ☆57Updated 3 months ago
• OpenPPL / ppl.nn.llm
  ☆140Updated 9 months ago
• triton-inference-server / paddlepaddle_backend
  ☆33Updated last year
• OpenPPL / ppl.llm.kernel.cuda
  ☆142Updated last month
• OpenPPL / ppl.llm.serving
  ☆127Updated last month
• PaddlePaddle / PaddleFleetX
  飞桨大模型开发套件，提供大语言模型、跨模态大模型、生物计算大模型等领域的全流程开发工具链。
  ☆454Updated 8 months ago
• PFCCLab / Camp
  飞桨护航计划集训营
  ☆19Updated this week
• harleyszhang / lite_llama
  A light llama-like llm inference framework based on the triton kernel.
  ☆88Updated this week
• OpenPPL / ppl.kernel.cuda
  ☆35Updated 4 months ago
• PaddlePaddle / Perf
  SOTA benchmark
  ☆18Updated last year
• ifromeast / cuda_learning
  learning how CUDA works
  ☆200Updated 6 months ago
• Oneflow-Inc / oneflow_convert
  OneFlow->ONNX
  ☆42Updated last year
• torchpipe / torchpipe
  Serving Inside Pytorch
  ☆154Updated this week
• Oneflow-Inc / DLPerf
  DeepLearning Framework Performance Profiling Toolkit
  ☆283Updated 2 years ago
• CalvinXKY / BasicCUDA
  A tutorial for CUDA&PyTorch
  ☆126Updated last month
• openmlsys / openmlsys-cuda
  Tutorials for writing high-performance GPU operators in AI frameworks.
  ☆128Updated last year
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆78Updated last month
• zjhellofss / KuiperCourse
  b站上的课程
  ☆71Updated last year
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆45Updated 3 months ago
• 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
  ☆474Updated 3 months ago
• PaddlePaddle / Paddle-bot
  ☆17Updated 3 weeks ago