Alternatives and similar repositories for tiny-flash-attention

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

• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆76Updated last year
• weishengying / cute_gemm
  ☆18Updated last year
• CalebDu / Awesome-Cute
  ☆107Updated 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.
  ☆41Updated 7 months ago
• OpenPPL / ppl.llm.kernel.cuda
  ☆150Updated 9 months ago
• zeroine / cutlass-cute-sample
  ☆44Updated last year
• Bruce-Lee-LY / cuda_hgemv
  Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
  ☆67Updated last year
• reed-lau / cute-gemm
  ☆137Updated 10 months ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆94Updated last month
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆62Updated 11 months ago
• NVIDIA / online-softmax
  Benchmark code for the "Online normalizer calculation for softmax" paper
  ☆102Updated 7 years ago
• AlibabaPAI / FLASHNN
  ☆100Updated last year
• pzhao-eng / FlashMLA
  ☆56Updated 3 months ago
• iclementine / optimize_softmax
  Optimize softmax in triton in many cases
  ☆21Updated last year
• DD-DuDa / Cute-Learning
  Examples of CUDA implementations by Cutlass CuTe
  ☆241Updated 3 months ago
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• AyakaGEMM / Hands-on-GEMM
  ☆141Updated 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
• MARD1NO / CUDA-PPT
  ☆109Updated 6 months ago
• nicolaswilde / cuda-sgemm
  ☆69Updated 9 months ago
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆96Updated 10 months ago
• Bruce-Lee-LY / cutlass_gemm
  Multiple GEMM operators are constructed with cutlass to support LLM inference.
  ☆20Updated 2 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.
  ☆45Updated 4 months ago
• BBuf / tensorrt-llm-moe
  ☆33Updated 8 months ago
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆112Updated last year
• JJXiangJiaoJun / cutlass_gemv
  GEMV implementation with CUTLASS
  ☆13Updated 2 months ago
• KuangjuX / NVSHMEM-Tutorial
  NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer
  ☆139Updated last month
• gty111 / GEMM_MMA
  Optimize GEMM with tensorcore step by step
  ☆32Updated last year
• ArthurinRUC / cutlass-notes
  From Minimal GEMM to Everything
  ☆58Updated 2 weeks ago
• jundaf2 / CUDA-INT8-GEMM
  CUDA 8-bit Tensor Core Matrix Multiplication based on m16n16k16 WMMA API
  ☆33Updated 2 years ago