Alternatives and similar repositories for Burst-Attention

Users that are interested in Burst-Attention are comparing it to the libraries listed below

• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆79Updated last year
• RulinShao / LightSeq
  Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training
  ☆221Updated last year
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆140Updated 7 months ago
• MayDomine / Seq1F1B
  Sequence-level 1F1B schedule for LLMs.
  ☆19Updated last year
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆110Updated 9 months ago
• Equationliu / Kangaroo
  [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…
  ☆64Updated last year
• madsys-dev / deepseekv2-profile
  ☆153Updated 10 months ago
• OpenBMB / infllmv2_cuda_impl
  ☆81Updated last month
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆113Updated 10 months ago
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆182Updated last month
• InternLM / turbomind
  ☆96Updated 9 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆109Updated 9 months ago
• microsoft / chunk-attention
  ☆84Updated 9 months ago
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆91Updated last year
• Dao-AILab / grouped-latent-attention
  ☆132Updated 7 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆154Updated 5 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆136Updated last year
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆176Updated last year
• flagos-ai / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆287Updated last year
• yanring / Megatron-MoE-ModelZoo
  Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.
  ☆152Updated last month
• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆257Updated 5 months ago
• kyegomez / FlashAttention20Triton
  Triton implementation of Flash Attention2.0
  ☆47Updated 2 years ago
• fzyzcjy / torch_utils
  Utility scripts for PyTorch (e.g. Make Perfetto show some disappearing kernels, Memory profiler that understands more low-level allocatio…
  ☆80Updated 4 months ago
• PipeFusion / PipeFusion
  A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters
  ☆55Updated last year
• AlibabaPAI / FLASHNN
  ☆104Updated last year
• linxihui / dkernel
  ☆21Updated 9 months ago
• rayleizhu / vllm-ra
  [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts
  ☆40Updated last year
• ModelTC / awesome-lm-system
  Summary of system papers/frameworks/codes/tools on training or serving large model
  ☆57Updated 2 years ago
• microsoft / AttentionEngine
  ☆117Updated 8 months ago
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆147Updated 3 weeks ago