Alternatives and similar repositories for AttentionEngine

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

• tile-ai / AttentionEngine
  ☆49Updated last month
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆44Updated 7 months ago
• flashinfer-ai / cutlass-viz
  ☆60Updated 2 months ago
• li-plus / flash-preference
  Accelerate LLM preference tuning via prefix sharing with a single line of code
  ☆42Updated last week
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆79Updated last week
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆70Updated 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
• PipeFusion / PipeFusion
  A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters
  ☆47Updated 11 months ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆69Updated 2 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆90Updated 2 weeks ago
• InternLM / turbomind
  ☆87Updated 3 months ago
• INT-FlashAttention2024 / INT-FlashAttention
  ☆77Updated 5 months ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆58Updated last month
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆101Updated last month
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆112Updated last year
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆40Updated last year
• tile-ai / TileOPs
  ☆42Updated last week
• microsoft / chunk-attention
  ☆77Updated 2 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆100Updated 3 months ago
• DD-DuDa / BitDecoding
  A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆52Updated this week
• AlibabaPAI / FLASHNN
  ☆96Updated 10 months ago
• Ascend / triton-ascend
  Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend
  ☆59Updated this week
• triton-lang / kernels
  ☆83Updated 8 months ago
• ModelTC / awesome-lm-system
  Summary of system papers/frameworks/codes/tools on training or serving large model
  ☆57Updated last year
• Dao-AILab / grouped-latent-attention
  ☆116Updated last month
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆110Updated 10 months ago
• fzyzcjy / torch_utils
  Utility scripts for PyTorch (e.g. Memory profiler that understands more low-level allocations such as NCCL)
  ☆15Updated last week
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆80Updated 10 months ago
• thunlp / TritonBench
  TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
  ☆62Updated last month
• pytorch-labs / tritonbench
  Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.
  ☆184Updated this week