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
  ☆51Updated last year
• aiha-lab / MX-QLLM
  LLM Inference with Microscaling Format
  ☆27Updated 9 months ago
• IST-DASLab / qutlass
  QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning
  ☆67Updated last month
• DD-DuDa / BitDecoding
  A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆57Updated 3 weeks ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆110Updated 2 months ago
• flashinfer-ai / cutlass-viz
  ☆61Updated 4 months ago
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆113Updated last year
• xxyux / SpInfer
  SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs
  ☆55Updated 5 months ago
• Dao-AILab / fast-hadamard-transform
  Fast Hadamard transform in CUDA, with a PyTorch interface
  ☆224Updated last year
• ChenMnZ / PrefixQuant
  An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization
  ☆147Updated 3 months ago
• naver-aics / lut-gemm
  ☆68Updated last year
• ruikangliu / FlatQuant
  [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"
  ☆153Updated last month
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆44Updated 9 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆138Updated last week
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆54Updated 7 months ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆71Updated 3 months ago
• 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.
  ☆40Updated 2 months ago
• SqueezeBits / QUICK
  QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
  ☆119Updated last year
• microsoft / SparTA
  ☆150Updated last year
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆95Updated 8 months ago
• Qualcomm-AI-research / gptvq
  ☆33Updated last year
• ByteDance-Seed / cudaLLM
  ☆91Updated last week
• DD-DuDa / BitDistiller
  [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.
  ☆120Updated last year
• microsoft / AttentionEngine
  ☆77Updated 3 months ago
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆319Updated last year
• tile-ai / AttentionEngine
  ☆50Updated 3 months ago
• PipeFusion / PipeFusion
  A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters
  ☆47Updated last year
• AlibabaPAI / FLASHNN
  ☆98Updated 11 months ago
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆261Updated last month
• IST-DASLab / FP-Quant
  ☆30Updated last week