Alternatives and similar repositories for fused-attention

Users that are interested in fused-attention are comparing it to the libraries listed below

• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆116Updated last year
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆111Updated last year
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆94Updated last month
• Bruce-Lee-LY / flash_attention_inference
  Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
  ☆41Updated 7 months ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆124Updated 4 months ago
• INT-FlashAttention2024 / INT-FlashAttention
  ☆82Updated 8 months ago
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆96Updated 10 months ago
• stanford-futuredata / stk
  ☆112Updated last year
• jundaf2 / INT8-Flash-Attention-FMHA-Quantization
  ☆158Updated 2 years ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆144Updated last month
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆320Updated last year
• IST-DASLab / qutlass
  QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning
  ☆114Updated 2 weeks ago
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆281Updated last year
• triton-lang / kernels
  ☆92Updated 11 months ago
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆265Updated 3 months ago
• microsoft / SparTA
  ☆152Updated last year
• AlibabaPAI / FLASHNN
  ☆100Updated last year
• Dao-AILab / fast-hadamard-transform
  Fast Hadamard transform in CUDA, with a PyTorch interface
  ☆248Updated this week
• Guangxuan-Xiao / torch-int
  This repository contains integer operators on GPUs for PyTorch.
  ☆219Updated 2 years ago
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆55Updated 9 months ago
• TiledTensor / TiledCUDA
  We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …
  ☆186Updated 8 months ago
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆169Updated last year
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆121Updated 5 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆98Updated 3 months ago
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆39Updated last year
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆83Updated last year
• nbasyl / LLM-FP4
  The official implementation of the EMNLP 2023 paper LLM-FP4
  ☆216Updated last year
• Bruce-Lee-LY / cuda_hgemv
  Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
  ☆67Updated last year
• NVIDIA / online-softmax
  Benchmark code for the "Online normalizer calculation for softmax" paper
  ☆101Updated 7 years ago
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆221Updated 2 years ago