Alternatives and similar repositories for libflash_attn:

Users that are interested in libflash_attn are comparing it to the libraries listed below

• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆87Updated 10 months ago
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆52Updated 5 months ago
• 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.
  ☆33Updated 4 months ago
• TiledTensor / TiledCUDA
  TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.
  ☆174Updated 2 months ago
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆93Updated 6 months ago
• AlibabaPAI / FLASHNN
  ☆78Updated 4 months ago
• zeroine / cutlass-cute-sample
  ☆25Updated 9 months ago
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆49Updated 6 months ago
• Bruce-Lee-LY / cuda_hgemv
  Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
  ☆54Updated 4 months ago
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆65Updated last month
• DefTruth / hgemm-tensorcores-mma
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, achieve peak⚡️ performance
  ☆43Updated this week
• LeiWang1999 / tvm_gpu_gemm
  play gemm with tvm
  ☆85Updated last year
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆38Updated 8 months ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆58Updated 2 months ago
• ColfaxResearch / cfx-article-src
  ☆66Updated 3 weeks ago
• CalebDu / Awesome-Cute
  ☆22Updated last month
• Bruce-Lee-LY / cutlass_gemm
  Multiple GEMM operators are constructed with cutlass to support LLM inference.
  ☆16Updated 3 months ago
• OpenPPL / ppl.kernel.cuda
  ☆33Updated 3 months ago
• OpenPPL / ppl.pmx
  ☆57Updated last month
• ColfaxResearch / cutlass-kernels
  ☆178Updated 6 months ago
• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for multi head attention (MHA) using CUDA core for the decoding stage of LLM inference.
  ☆27Updated 2 months ago
• microsoft / TileFusion
  ☆36Updated this week
• MARD1NO / CUDA-PPT
  ☆79Updated last year
• NVIDIA / online-softmax
  Benchmark code for the "Online normalizer calculation for softmax" paper
  ☆62Updated 6 years ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆94Updated last month
• OpenPPL / ppl.llm.kernel.cuda
  ☆141Updated last week
• InternLM / turbomind
  ☆52Updated last month
• gty111 / GEMM_MMA
  Optimize GEMM with tensorcore step by step
  ☆19Updated last year
• OpenPPL / ppl.nn.llm
  ☆140Updated 8 months ago
• DD-DuDa / Cute-Learning
  Examples of CUDA implementations by Cutlass CuTe
  ☆127Updated last month