Alternatives and similar repositories for Awesome-Efficient-LLM:

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

• jiazhihao / attention_superoptimizer
  An Attention Superoptimizer
  ☆21Updated 2 months ago
• LeiWang1999 / Stream-k.tvm
  ☆19Updated 6 months 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 …
  ☆24Updated 3 months ago
• zhuzilin / pytorch-malloc
  An external memory allocator example for PyTorch.
  ☆14Updated 3 years ago
• sjtu-epcc / Tacker
  Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS
  ☆21Updated last month
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆31Updated 3 weeks ago
• chips-compilers-mlsys-21 / chips-compilers-mlsys-21.github.io
  ☆11Updated 3 years ago
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆45Updated 4 months ago
• INT-FlashAttention2024 / INT-FlashAttention
  ☆67Updated 2 months ago
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆38Updated 11 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆74Updated this week
• WukLab / preble
  Stateful LLM Serving
  ☆50Updated 2 weeks ago
• AutonomicPerfectionist / PipeInfer
  PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation
  ☆28Updated 4 months ago
• facebookresearch / MODel_opt
  Memory Optimizations for Deep Learning (ICML 2023)
  ☆62Updated last year
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆63Updated 2 weeks ago
• hao-ai-lab / MuxServe
  ☆55Updated 9 months ago
• chhzh123 / ptc-tutorial
  PyTorch compilation tutorial covering TorchScript, torch.fx, and Slapo
  ☆18Updated 2 years ago
• illinois-impact / klap
  A source-to-source compiler for optimizing CUDA dynamic parallelism by aggregating launches
  ☆15Updated 5 years ago
• MDK8888 / vllmini
  A minimal implementation of vllm.
  ☆37Updated 8 months ago
• mlc-ai / mlc-python
  ☆26Updated last week
• Raincleared-Song / sparse_gpu_operator
  GPU operators for sparse tensor operations
  ☆31Updated last year
• dywsjtu / apparate
  Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]
  ☆22Updated 4 months ago
• tile-ai / tvm
  Open deep learning compiler stack for cpu, gpu and specialized accelerators
  ☆18Updated last week
• flashinfer-ai / debug-print
  Debug print operator for cudagraph debugging
  ☆10Updated 7 months ago
• microsoft / AttentionEngine
  ☆52Updated this week
• bytedance / QSync
  Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".
  ☆19Updated last year
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆63Updated last week
• DD-DuDa / BitDecoding
  A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆23Updated this week
• Chtholly-Boss / swizzle
  A practical way of learning Swizzle
  ☆16Updated last month
• sgl-project / tensorrt-demo
  TensorRT LLM Benchmark Configuration
  ☆13Updated 8 months ago