Alternatives and similar repositories for Awesome-Efficient-LLM

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

• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆90Updated 3 months ago
• chhzh123 / ptc-tutorial
  PyTorch compilation tutorial covering TorchScript, torch.fx, and Slapo
  ☆17Updated 2 years ago
• microsoft / FractalTensor
  FractalTensor is a programming framework that introduces a novel approach to organizing data in deep neural networks (DNNs) as a list of …
  ☆31Updated last year
• xxyux / SpInfer
  SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs
  ☆59Updated 8 months ago
• LeiWang1999 / Stream-k.tvm
  ☆19Updated last year
• INT-FlashAttention2024 / INT-FlashAttention
  ☆83Updated 10 months ago
• Infini-AI-Lab / vortex_torch
  Vortex: A Flexible and Efficient Sparse Attention Framework
  ☆43Updated 2 weeks ago
• Qualcomm-AI-research / gptvq
  ☆37Updated last year
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆49Updated 4 months ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆73Updated 7 months ago
• zhuzilin / pytorch-malloc
  An external memory allocator example for PyTorch.
  ☆16Updated 4 months ago
• sjtu-epcc / DVABatch
  ☆21Updated 3 years ago
• microsoft / tokenweave
  Efficient Compute-Communication Overlap for Distributed LLM Inference
  ☆66Updated last month
• argonne-lcf / LLM-Inference-Bench
  LLM-Inference-Bench
  ☆56Updated 5 months ago
• uwsampl / SparseTIR
  SparseTIR: Sparse Tensor Compiler for Deep Learning
  ☆140Updated 2 years ago
• tile-ai / TileOPs
  ☆63Updated this week
• Raincleared-Song / sparse_gpu_operator
  GPU operators for sparse tensor operations
  ☆35Updated last year
• flashinfer-ai / debug-print
  Debug print operator for cudagraph debugging
  ☆14Updated last year
• tyler-griggs / melange-release
  ☆48Updated last year
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆105Updated 5 months ago
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆41Updated last year
• tile-ai / AttentionEngine
  ☆52Updated 7 months ago
• Ying1123 / llm-caching-multiplexing
  ☆20Updated 2 years ago
• AutonomicPerfectionist / PipeInfer
  PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation
  ☆31Updated last year
• eth-easl / deltazip
  Compression for Foundation Models
  ☆34Updated 4 months ago
• mit-han-lab / tinychat-tutorial
  ☆76Updated last year
• jiazhihao / attention_superoptimizer
  An Attention Superoptimizer
  ☆22Updated 11 months ago
• sspec-project / SparseSpec
  Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
  ☆62Updated 2 weeks ago
• casys-kaist / EnvPipe
  ☆25Updated 2 years ago
• ruipeterpan / marconi
  Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]
  ☆47Updated 9 months ago