Alternatives and similar repositories for INT-FlashAttention

Users that are interested in INT-FlashAttention are comparing it to the libraries listed below

• thu-ml / Jetfire-INT8Training
  ☆53Updated last year
• DD-DuDa / BitDecoding
  A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆60Updated last month
• aiha-lab / MX-QLLM
  LLM Inference with Microscaling Format
  ☆31Updated 10 months ago
• flashinfer-ai / cutlass-viz
  ☆64Updated 5 months ago
• IST-DASLab / qutlass
  QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning
  ☆111Updated last week
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆123Updated 4 months ago
• xxyux / SpInfer
  SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs
  ☆59Updated 6 months ago
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆44Updated 10 months ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆71Updated 5 months ago
• ruikangliu / FlatQuant
  [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"
  ☆170Updated last week
• Qualcomm-AI-research / gptvq
  ☆35Updated last year
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆116Updated last year
• ByteDance-Seed / cudaLLM
  ☆115Updated last month
• naver-aics / lut-gemm
  ☆72Updated last year
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆96Updated 9 months ago
• ChenMnZ / PrefixQuant
  An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization
  ☆150Updated 4 months ago
• SqueezeBits / QUICK
  QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
  ☆118Updated last year
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆55Updated 8 months ago
• microsoft / AttentionEngine
  ☆99Updated 4 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆141Updated last month
• microsoft / SparTA
  ☆151Updated last year
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆320Updated last year
• tile-ai / AttentionEngine
  ☆50Updated 4 months ago
• Intelligent-Computing-Lab-Panda / GPTAQ
  Code implementation of GPTAQ (https://arxiv.org/abs/2504.02692)
  ☆65Updated 2 months ago
• Dao-AILab / fast-hadamard-transform
  Fast Hadamard transform in CUDA, with a PyTorch interface
  ☆245Updated last week
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆105Updated 6 months ago
• AlibabaPAI / FLASHNN
  ☆98Updated last year
• ruipeterpan / marconi
  Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]
  ☆37Updated 7 months ago
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆265Updated 2 months ago
• FasterDecoding / TEAL
  ☆143Updated 7 months ago