Alternatives and similar repositories for flash-attention-turing

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

• Repeerc / flash-attention-v2-RDNA3-minimal
  a simple Flash Attention v2 implementation with ROCM (RDNA3 GPU, roc wmma), mainly used for stable diffusion(ComfyUI) in Windows ZLUDA en…
  ☆48Updated last year
• ROCm / flash-attention
  Fast and memory-efficient exact attention
  ☆193Updated last week
• IST-DASLab / marlin
  FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
  ☆916Updated last year
• ModelCloud / GPTQModel
  LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU vi…
  ☆842Updated this week
• vllm-project / compressed-tensors
  A safetensors extension to efficiently store sparse quantized tensors on disk
  ☆180Updated this week
• nunchaku-tech / deepcompressor
  Model Compression Toolbox for Large Language Models and Diffusion Models
  ☆671Updated 2 months ago
• neuralmagic / AutoFP8
  ☆205Updated 5 months ago
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆265Updated 3 months ago
• LeanModels / DFloat11
  DFloat11: Lossless LLM Compression for Efficient GPU Inference
  ☆550Updated 2 months ago
• mlc-ai / relax
  ☆167Updated this week
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆144Updated 2 months ago
• microsoft / BitBLAS
  BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
  ☆698Updated 2 months ago
• ReinForce-II / mmapeak
  ☆43Updated 3 weeks ago
• modelscope / dash-infer
  DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …
  ☆266Updated 2 months ago
• Cornell-RelaxML / qtip
  ☆152Updated 4 months ago
• intel / xFasterTransformer
  ☆430Updated last month
• ROCm / vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆108Updated last week
• mit-han-lab / omniserve
  [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…
  ☆766Updated 7 months ago
• OpenBMB / CPM.cu
  CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…
  ☆199Updated 2 weeks ago
• intel / auto-round
  Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU.
  ☆668Updated this week
• ROCm / triton
  Development repository for the Triton language and compiler
  ☆137Updated this week
• OpenGVLab / EfficientQAT
  [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models
  ☆306Updated 5 months ago
• ubergarm / r1-ktransformers-guide
  run DeepSeek-R1 GGUFs on KTransformers
  ☆253Updated 7 months ago
• FlagOpen / FlagCX
  ☆91Updated last week
• sgl-project / SpecForge
  Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
  ☆439Updated this week
• aikitoria / open-gpu-kernel-modules
  NVIDIA Linux open GPU with P2P support
  ☆66Updated 2 weeks ago
• ROCm / AITemplate
  AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…
  ☆12Updated last year
• Dao-AILab / fast-hadamard-transform
  Fast Hadamard transform in CUDA, with a PyTorch interface
  ☆248Updated last week
• ROCm / aotriton
  Ahead of Time (AOT) Triton Math Library
  ☆79Updated last week
• zhaochenyang20 / ModelServer
  Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang
  ☆58Updated 11 months ago