Alternatives and similar repositories for FlashMLA

Users that are interested in FlashMLA 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
  ☆78Updated last year
• CalebDu / Awesome-Cute
  ☆112Updated 7 months ago
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆97Updated last year
• AlibabaPAI / FLASHNN
  ☆102Updated last year
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆137Updated 7 months ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆96Updated 3 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.
  ☆43Updated 9 months ago
• OpenPPL / ppl.llm.kernel.cuda
  ☆152Updated 11 months ago
• weishengying / tiny-flash-attention
  使用 cutlass 实现 flash-attention 精简版，具有教学意义
  ☆51Updated last year
• flashinfer-ai / cutlass-viz
  ☆65Updated 7 months ago
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆112Updated last year
• DD-DuDa / Cute-Learning
  Examples of CUDA implementations by Cutlass CuTe
  ☆260Updated 5 months ago
• zeroine / cutlass-cute-sample
  ☆48Updated last year
• BBuf / tensorrt-llm-moe
  ☆33Updated 10 months ago
• xlite-dev / ffpa-attn
  🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
  ☆239Updated last month
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆196Updated 2 months ago
• madsys-dev / deepseekv2-profile
  ☆153Updated 9 months ago
• InternLM / turbomind
  ☆97Updated 8 months ago
• Bruce-Lee-LY / cuda_hgemv
  Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
  ☆70Updated last year
• ColfaxResearch / cutlass-kernels
  ☆249Updated last year
• OpenBitSys / BitDecoding
  [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆69Updated last week
• TiledTensor / TiledCUDA
  We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …
  ☆190Updated 10 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆151Updated 3 months ago
• KuangjuX / NVSHMEM-Tutorial
  NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer
  ☆146Updated 3 months ago
• reed-lau / cute-gemm
  ☆154Updated last month
• dsl-learn / cutile-learn
  NVIDIA cuTile learn
  ☆119Updated last week
• OpenPPL / ppl.nn.llm
  ☆140Updated last year
• gty111 / GEMM_MMA
  Optimize GEMM with tensorcore step by step
  ☆36Updated 2 years ago
• Ascend / triton-ascend
  Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend
  ☆90Updated this week
• iclementine / optimize_softmax
  Optimize softmax in triton in many cases
  ☆21Updated last year