Alternatives and similar repositories for FlagAttention

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

• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆145Updated 3 weeks ago
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆265Updated 2 months ago
• Guangxuan-Xiao / torch-int
  This repository contains integer operators on GPUs for PyTorch.
  ☆216Updated last year
• ColfaxResearch / cutlass-kernels
  ☆231Updated last year
• madsys-dev / deepseekv2-profile
  ☆147Updated 6 months ago
• 66RING / tiny-flash-attention
  flash attention tutorial written in python, triton, cuda, cutlass
  ☆417Updated 4 months ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆116Updated 3 months ago
• meta-pytorch / applied-ai
  Applied AI experiments and examples for PyTorch
  ☆294Updated 3 weeks ago
• AlibabaPAI / FLASHNN
  ☆98Updated last year
• sail-sg / zero-bubble-pipeline-parallelism
  Zero Bubble Pipeline Parallelism
  ☆426Updated 4 months ago
• meta-pytorch / tritonbench
  Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.
  ☆223Updated this week
• KnowingNothing / MatmulTutorial
  A Easy-to-understand TensorOp Matmul Tutorial
  ☆376Updated 11 months ago
• FlagOpen / FlagGems
  FlagGems is an operator library for large language models implemented in the Triton Language.
  ☆673Updated last week
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆320Updated last year
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆106Updated 5 months ago
• microsoft / vattention
  Dynamic Memory Management for Serving LLMs without PagedAttention
  ☆416Updated 3 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.
  ☆217Updated last month
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆139Updated 3 weeks 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.
  ☆40Updated 6 months ago
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆220Updated last year
• Dao-AILab / fast-hadamard-transform
  Fast Hadamard transform in CUDA, with a PyTorch interface
  ☆233Updated 2 weeks ago
• Victarry / PP-Schedule-Visualization
  Pipeline Parallelism Emulation and Visualization
  ☆66Updated 3 months ago
• InternLM / turbomind
  ☆94Updated 5 months ago
• sgl-project / SpecForge
  Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
  ☆400Updated this week
• gpu-mode / triton-index
  Cataloging released Triton kernels.
  ☆257Updated last week
• OpenPPL / ppl.nn.llm
  ☆141Updated last year
• fzyzcjy / torch_memory_saver
  Allow torch tensor memory to be released and resumed later
  ☆133Updated last week
• yanring / Megatron-MoE-ModelZoo
  Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.
  ☆89Updated last week
• RulinShao / LightSeq
  Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training
  ☆216Updated last year
• Dao-AILab / quack
  A Quirky Assortment of CuTe Kernels
  ☆519Updated this week