Alternatives and similar repositories for FlashAttention20

Users that are interested in FlashAttention20 are comparing it to the libraries listed below

• haochengxi / Train_Transformers_with_INT4
  ☆154Updated 2 years ago
• OpenNLPLab / lightning-attention
  Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
  ☆328Updated 6 months ago
• tridao / flash-attention-wheels
  ☆56Updated last year
• hahnyuan / RPTQ4LLM
  Reorder-based post-training quantization for large language model
  ☆195Updated 2 years ago
• thu-ml / low-bit-optimizers
  Low-bit optimizers for PyTorch
  ☆131Updated last year
• hahnyuan / PB-LLM
  PB-LLM: Partially Binarized Large Language Models
  ☆153Updated last year
• Dao-AILab / grouped-latent-attention
  ☆126Updated 3 months ago
• nbasyl / LLM-FP4
  The official implementation of the EMNLP 2023 paper LLM-FP4
  ☆214Updated last year
• kyegomez / FlashAttention20Triton
  Triton implementation of Flash Attention2.0
  ☆39Updated 2 years ago
• wejoncy / QLLM
  A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.
  ☆177Updated 5 months ago
• nil0x9 / flash-muon
  Flash-Muon: An Efficient Implementation of Muon Optimizer
  ☆185Updated 3 months ago
• ChenMnZ / PrefixQuant
  An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization
  ☆148Updated 3 months ago
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆165Updated last year
• pan-x-c / EE-LLM
  EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).
  ☆67Updated last year
• Macaronlin / LLaMA3-Quantization
  A repository dedicated to evaluating the performance of quantizied LLaMA3 using various quantization methods..
  ☆194Updated 8 months ago
• astramind-ai / Mixture-of-depths
  Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
  ☆170Updated last year
• SqueezeAILab / KVQuant
  [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
  ☆381Updated last year
• thu-nics / MoA
  [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>
  ☆146Updated 2 months ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆116Updated 3 months ago
• FasterDecoding / TEAL
  ☆141Updated 7 months ago
• chu-tianxiang / QuIP-for-all
  QuIP quantization
  ☆59Updated last year
• Dao-AILab / fast-hadamard-transform
  Fast Hadamard transform in CUDA, with a PyTorch interface
  ☆233Updated last week
• stanford-futuredata / stk
  ☆111Updated last year
• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆239Updated last month
• amazon-science / mxfp4-llm
  Official implementation for Training LLMs with MXFP4
  ☆89Updated 4 months ago
• IsaacRe / vllm-kvcompress
  KV cache compression for high-throughput LLM inference
  ☆136Updated 7 months ago
• jundaf2 / INT8-Flash-Attention-FMHA-Quantization
  ☆159Updated 2 years ago
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆105Updated 5 months ago
• NVIDIA / Star-Attention
  Efficient LLM Inference over Long Sequences
  ☆391Updated 2 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆126Updated 9 months ago