Alternatives and similar repositories for Awesome-Efficient-LLM

Users that are interested in Awesome-Efficient-LLM are comparing it to the libraries listed below

• LeiWang1999 / Stream-k.tvm
  ☆19Updated 9 months ago
• jiazhihao / attention_superoptimizer
  An Attention Superoptimizer
  ☆21Updated 5 months ago
• chhzh123 / ptc-tutorial
  PyTorch compilation tutorial covering TorchScript, torch.fx, and Slapo
  ☆18Updated 2 years ago
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆39Updated 2 months ago
• zhuzilin / pytorch-malloc
  An external memory allocator example for PyTorch.
  ☆14Updated 3 years ago
• xxyux / SpInfer
  SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs
  ☆48Updated 3 months ago
• tile-ai / AttentionEngine
  ☆49Updated last month
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆69Updated last month
• tonyzhang617 / nomad-dist
  ☆34Updated last year
• flashinfer-ai / cutlass-viz
  ☆60Updated 2 months ago
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆40Updated last year
• hao-ai-lab / MuxServe
  ☆62Updated last year
• microsoft / FractalTensor
  FractalTensor is a programming framework that introduces a novel approach to organizing data in deep neural networks (DNNs) as a list of …
  ☆26Updated 6 months ago
• casys-kaist / EnvPipe
  ☆25Updated last year
• zhisbug / Cavs
  Cavs: An Efficient Runtime System for Dynamic Neural Networks
  ☆14Updated 4 years ago
• sjtu-epcc / Tacker
  Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS
  ☆27Updated 4 months ago
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆77Updated last week
• Raincleared-Song / sparse_gpu_operator
  GPU operators for sparse tensor operations
  ☆33Updated last year
• msr-fiddle / harmony
  ☆16Updated 2 years ago
• bytedance / QSync
  Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".
  ☆20Updated last year
• osayamenja / Kleos
  Complete GPU residency for ML.
  ☆17Updated last week
• cassiewilliam / cuda_op_benchmark
  方便扩展的Cuda算子理解和优化框架，仅用在学习使用
  ☆15Updated last year
• AutonomicPerfectionist / PipeInfer
  PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation
  ☆30Updated 7 months ago
• INT-FlashAttention2024 / INT-FlashAttention
  ☆75Updated 5 months ago
• abhibambhaniya / GenZ-LLM-Analyzer
  LLM Inference analyzer for different hardware platforms
  ☆74Updated last month
• flashinfer-ai / debug-print
  Debug print operator for cudagraph debugging
  ☆11Updated 10 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆90Updated 3 weeks ago
• VITA-Group / Q-Hitter
  ☆14Updated last year
• li-plus / flash-preference
  Accelerate LLM preference tuning via prefix sharing with a single line of code
  ☆41Updated last month
• microsoft / AttentionEngine
  ☆71Updated last month