Alternatives and similar repositories for SRDA

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

• microsoft / AttentionEngine
  ☆92Updated 3 months ago
• ByteDance-Seed / cudaLLM
  ☆99Updated 2 weeks ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆70Updated 3 months ago
• tile-ai / AttentionEngine
  ☆50Updated 3 months ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆69Updated 2 months ago
• flashinfer-ai / cutlass-viz
  ☆63Updated 4 months ago
• InternLM / turbomind
  ☆93Updated 5 months ago
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆44Updated 9 months ago
• PipeFusion / PipeFusion
  A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters
  ☆47Updated last year
• KuangjuX / AttnLink
  An experimental communicating attention kernel based on DeepEP.
  ☆34Updated last month
• Ascend / triton-ascend
  Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend
  ☆68Updated this week
• tile-ai / tilescale
  Tile-based language built for AI computation across all scales
  ☆47Updated last week
• OpenBMB / CPM.cu
  CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…
  ☆175Updated last week
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆109Updated 3 months ago
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆81Updated 2 weeks ago
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆76Updated last year
• mit-han-lab / tinychat-tutorial
  ☆72Updated 10 months ago
• 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.
  ☆40Updated 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.
  ☆95Updated 2 months ago
• INT-FlashAttention2024 / INT-FlashAttention
  ☆81Updated 7 months ago
• Dao-AILab / grouped-latent-attention
  ☆124Updated 3 months ago
• xlite-dev / ffpa-attn
  🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
  ☆212Updated 3 weeks ago
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆136Updated 3 months ago
• CalvinXKY / mfu_calculation
  A simple calculation for LLM MFU.
  ☆44Updated 6 months ago
• ademeure / cuda-side-boost
  ☆42Updated 3 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆104Updated 5 months ago
• li-plus / flash-preference
  Accelerate LLM preference tuning via prefix sharing with a single line of code
  ☆43Updated 2 months ago
• xdit-project / DiTCacheAnalysis
  An auxiliary project analysis of the characteristics of KV in DiT Attention.
  ☆32Updated 9 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆125Updated 9 months ago
• OpenBMB / infllmv2_cuda_impl
  ☆46Updated 2 months ago