Alternatives and similar repositories for FlashAttention20Triton:

Users that are interested in FlashAttention20Triton are comparing it to the libraries listed below

• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆64Updated 8 months ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆64Updated 3 months ago
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆64Updated 5 months ago
• stanford-futuredata / stk
  ☆100Updated 5 months ago
• RulinShao / LightSeq
  Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers
  ☆205Updated 6 months ago
• InternLM / turbomind
  ☆67Updated 2 months ago
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆84Updated 4 months ago
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆157Updated 7 months ago
• sail-sg / VocabularyParallelism
  Vocabulary Parallelism
  ☆17Updated 3 months ago
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆94Updated last month
• ModelTC / awesome-lm-system
  Summary of system papers/frameworks/codes/tools on training or serving large model
  ☆56Updated last year
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆107Updated 2 months ago
• AlibabaPAI / FLASHNN
  ☆81Updated 5 months ago
• NVlabs / COAT
  ☆87Updated this week
• Equationliu / Kangaroo
  [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…
  ☆48Updated 7 months ago
• FasterDecoding / TEAL
  ☆111Updated this week
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆97Updated 7 months ago
• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for multi head attention (MHA) using CUDA core for the decoding stage of LLM inference.
  ☆29Updated 3 months ago
• microsoft / chunk-attention
  ☆62Updated 2 months ago
• madsys-dev / deepseekv2-profile
  ☆104Updated 6 months ago
• thu-pacman / FasterMoE
  ☆76Updated 2 years ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆77Updated this week
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆245Updated 2 months ago
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆295Updated 7 months ago
• deepspeedai / DeepSpeed-Kernels
  ☆59Updated 2 weeks ago
• INT-FlashAttention2024 / INT-FlashAttention
  ☆61Updated 3 weeks ago
• pytorch-labs / tritonbench
  Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.
  ☆89Updated this week
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆34Updated 2 months ago
• d-matrix-ai / keyformer-llm
  ☆52Updated 10 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆101Updated this week