Alternatives and similar repositories for flash-attention-v100

Users that are interested in flash-attention-v100 are comparing it to the libraries listed below

• hyperai / triton-cn
  Triton Documentation in Chinese Simplified / Triton 中文文档
  ☆74Updated 3 months ago
• mdy666 / mdy_triton
  ☆140Updated 2 weeks ago
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆58Updated 8 months ago
• xlite-dev / ffpa-attn
  ⚡️FFPA: Extend FlashAttention-2 with Split-D, achieve ~O(1) SRAM complexity for large headdim, 1.8x~3x↑ vs SDPA.🎉
  ☆192Updated 2 months ago
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆98Updated last week
• openmlsys / openmlsys-cuda
  Tutorials for writing high-performance GPU operators in AI frameworks.
  ☆129Updated last year
• modelscope / dash-infer
  DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …
  ☆259Updated last month
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆102Updated 3 months ago
• Ascend / AscendSpeed
  ☆79Updated last year
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆108Updated last year
• OpenPPL / ppl.llm.serving
  ☆128Updated 6 months ago
• AyakaGEMM / Hands-on-GEMM
  ☆137Updated last year
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• madsys-dev / deepseekv2-profile
  ☆145Updated 4 months ago
• DeepLink-org / dlinfer
  ☆53Updated 2 weeks ago
• OpenNLPLab / lightning-attention
  Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
  ☆323Updated 4 months ago
• Rayrtfr / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆17Updated last year
• AlibabaPAI / FLASHNN
  ☆96Updated 10 months ago
• Tlntin / qwen-ascend-llm
  ☆47Updated 8 months ago
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆272Updated last year
• 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.
  ☆38Updated last month
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆135Updated 3 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…
  ☆160Updated last week
• luchangli03 / onnxsim_large_model
  simplify >2GB large onnx model
  ☆60Updated 7 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.
  ☆39Updated 4 months ago
• BBuf / megatron-lm-parallel-group-playground
  ☆16Updated last year
• yuunnn-w / RWKV_Pytorch
  This is an inference framework for the RWKV large language model implemented purely in native PyTorch. The official native implementation…
  ☆130Updated 11 months ago
• ByteDance-Seed / decoupleQ
  A quantization algorithm for LLM
  ☆141Updated last year
• iclementine / optimize_softmax
  Optimize softmax in triton in many cases
  ☆21Updated 10 months ago
• DD-DuDa / BitDistiller
  [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.
  ☆115Updated last year