Alternatives and similar repositories for Awesome-Efficient-LLM:

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

• 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 4 months ago
• zhuzilin / pytorch-malloc
  An external memory allocator example for PyTorch.
  ☆14Updated 3 years ago
• 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
  ☆13Updated 10 months ago
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆35Updated last week
• sjtu-epcc / Tacker
  Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS
  ☆25Updated 2 months ago
• LeiWang1999 / Stream-k.tvm
  ☆19Updated 6 months ago
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆38Updated last year
• INT-FlashAttention2024 / INT-FlashAttention
  ☆68Updated 3 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆82Updated this week
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆45Updated 5 months ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆67Updated 3 weeks ago
• chhzh123 / ptc-tutorial
  PyTorch compilation tutorial covering TorchScript, torch.fx, and Slapo
  ☆18Updated 2 years ago
• xxyux / SpInfer
  SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs
  ☆42Updated last month
• flashinfer-ai / cutlass-viz
  ☆55Updated 2 weeks ago
• bytedance / QSync
  Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".
  ☆19Updated last year
• microsoft / chunk-attention
  ☆69Updated last week
• Qualcomm-AI-research / gptvq
  ☆29Updated last year
• hgyhungry / alcop-artifact
  ☆22Updated 2 years ago
• jiazhihao / attention_superoptimizer
  An Attention Superoptimizer
  ☆21Updated 3 months ago
• tile-ai / tvm
  Open deep learning compiler stack for cpu, gpu and specialized accelerators
  ☆18Updated last week
• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.
  ☆36Updated 3 weeks ago
• apuaaChen / EVT_AE
  Artifacts of EVT ASPLOS'24
  ☆23Updated last year
• uwsampl / SparseTIR
  SparseTIR: Sparse Tensor Compiler for Deep Learning
  ☆135Updated 2 years ago
• hao-ai-lab / MuxServe
  ☆59Updated 10 months ago
• illinois-impact / klap
  A source-to-source compiler for optimizing CUDA dynamic parallelism by aggregating launches
  ☆15Updated 5 years ago
• VITA-Group / Q-Hitter
  ☆13Updated 10 months ago
• chips-compilers-mlsys-21 / chips-compilers-mlsys-21.github.io
  ☆11Updated 4 years ago
• lightmatter-ai / INT-FP-QSim
  Flexible simulator for mixed precision and format simulation of LLMs and vision transformers.
  ☆49Updated last year
• ucamrl / xrlflow
  ☆14Updated 2 years ago
• amazon-science / FeatGraph
  ☆71Updated 3 years ago