Alternatives and similar repositories for Starter

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

• PFCCLab / Camp
  飞桨护航计划集训营
  ☆21Updated last month
• hyperai / triton-cn
  Triton Documentation in Chinese Simplified / Triton 中文文档
  ☆82Updated 5 months ago
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆62Updated 10 months ago
• PaddlePaddle / community
  PaddlePaddle Developer Community
  ☆124Updated this week
• xlite-dev / ffpa-attn
  🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
  ☆218Updated last month
• YuxueYang1204 / CudaDemo
  Implement custom operators in PyTorch with cuda/c++
  ☆71Updated 2 years ago
• harleyszhang / lite_llama
  A light llama-like llm inference framework based on the triton kernel.
  ☆152Updated last month
• LDLINGLINGLING / nano_vllm_note
  注释的nano_vllm仓库，并且完成了MiniCPM4的适配以及注册新模型的功能
  ☆75Updated last month
• InfiniTensor / RefactorGraph
  分层解耦的深度学习推理引擎
  ☆75Updated 7 months ago
• InfiniTensor / InfiniTensor
  ☆255Updated this week
• PaddlePaddle / PaConvert
  PaddlePaddle Code Convert Toolkit. 『飞桨』深度学习代码转换工具
  ☆112Updated this week
• ZRayZzz / flash-attention-v100
  ☆55Updated last year
• PaddlePaddle / PaddleCustomDevice
  PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)
  ☆95Updated this week
• openmlsys / openmlsys-cuda
  Tutorials for writing high-performance GPU operators in AI frameworks.
  ☆131Updated 2 years ago
• zjhellofss / kuiperdatawhale
  ☆296Updated 11 months ago
• li199603 / parallel_prefix_sum
  Parallel Prefix Sum (Scan) with CUDA
  ☆25Updated last year
• ZonePG / cs-notes
  my cs notes
  ☆56Updated 11 months ago
• OpenMLIR / TritonLLM
  LLM Inference via Triton (Flexible & Modular): Focused on Kernel Optimization using CUBIN binaries, Starting from gpt-oss Model
  ☆40Updated 2 weeks ago
• xgqdut2016 / hpc_project
  some hpc project for learning
  ☆24Updated last year
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆106Updated 2 months ago
• xgqdut2016 / cuda_code
  easy cuda code
  ☆83Updated 8 months ago
• zjhellofss / KuiperCourse
  b站上的课程
  ☆75Updated 2 years ago
• mdy666 / mdy_triton
  ☆143Updated 2 months ago
• DeepLink-org / dlinfer
  ☆61Updated last week
• BBuf / how-to-learn-deep-learning-framework
  how to learn PyTorch and OneFlow
  ☆453Updated last year
• PFCCLab / blog
  PFCC 社区博客
  ☆12Updated this week
• CalvinXKY / mfu_calculation
  A simple calculation for LLM MFU.
  ☆45Updated last week
• interestingLSY / CUDA-From-Correctness-To-Performance-Code
  Codes & examples for "CUDA - From Correctness to Performance"
  ☆111Updated 10 months ago
• InternLM / turbomind
  ☆95Updated 5 months ago
• zhaochenyang20 / ModelServer
  Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang
  ☆56Updated 10 months ago