Alternatives and similar repositories for genesis

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

• gogongxt / nano-sglang
  ☆44Updated last month
• xlite-dev / ffpa-attn
  🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
  ☆231Updated last week
• DeepLink-org / DLSlime
  DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
  ☆82Updated this week
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆97Updated 11 months ago
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆40Updated last year
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆129Updated 6 months ago
• toyaix / triton-runner
  Multi-Level Triton Runner supporting Python, IR, PTX, and cubin.
  ☆76Updated 2 weeks ago
• TiledTensor / TiledCUDA
  We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …
  ☆190Updated 10 months ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆90Updated 5 months ago
• gty111 / gLLM
  gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling
  ☆51Updated last week
• 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
  ☆101Updated 3 months ago
• interestingLSY / CUDA-From-Correctness-To-Performance-Code
  Codes & examples for "CUDA - From Correctness to Performance"
  ☆117Updated last year
• sonnyli / flash_attention_from_scratch
  Flash Attention from Scratch on CUDA Ampere
  ☆76Updated 2 months ago
• InternLM / Awesome-LLM-Training-System
  ☆44Updated last year
• Chtholly-Boss / swizzle
  A practical way of learning Swizzle
  ☆33Updated 9 months ago
• Sunt-ing / stick
  A PyTorch-like deep learning framework. Just for fun.
  ☆156Updated 2 years ago
• mdy666 / mdy_triton
  ☆149Updated 4 months ago
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆113Updated 4 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆102Updated 5 months ago
• heheda12345 / MagPy
  ☆40Updated last year
• tsinghua-ideal / Canvas
  Canvas: End-to-End Kernel Architecture Search in Neural Networks
  ☆26Updated last year
• CalebDu / Awesome-Cute
  ☆112Updated 6 months ago
• ByteDance-Seed / cudaLLM
  ☆125Updated 3 months ago
• zhuzilin / flash-attention-with-sink
  ☆39Updated 3 months ago
• InfiniTensor / InfiniTensor
  ☆274Updated last month
• eedalong / ECE408
  Code base and slides for ECE408：Applied Parallel Programming On GPU.
  ☆138Updated 4 years ago
• LeiWang1999 / tvm_gpu_gemm
  play gemm with tvm
  ☆92Updated 2 years ago
• ailzhang / EfficientPyTorch
  Code release for book "Efficient Training in PyTorch"
  ☆112Updated 7 months ago
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆62Updated last year
• Ascend / triton-ascend
  Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend
  ☆84Updated last week