Alternatives and similar repositories for APPy:

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

• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆45Updated 5 months ago
• GindaChen / FlexFlashAttention3
  FlexAttention w/ FlashAttention3 Support
  ☆26Updated 7 months ago
• nil0x9 / flash-muon
  Flash-Muon: An Efficient Implementation of Muon Optimzer
  ☆91Updated this week
• Dao-AILab / gemm-cublas
  ☆17Updated last week
• dame-cell / Triformer
  Transformers components but in Triton
  ☆33Updated last month
• li-plus / flash-preference
  Accelerate LLM preference tuning via prefix sharing with a single line of code
  ☆40Updated last week
• sustcsonglin / fla-tilelang
  ☆20Updated 2 months ago
• mayank31398 / cute-kernels
  A bunch of kernels that might make stuff slower 😉
  ☆40Updated this week
• Doraemonzzz / Awesome-Triton-Resources
  Awesome Triton Resources
  ☆27Updated last week
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆70Updated this week
• pytorch-labs / tritonbench
  Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.
  ☆122Updated this week
• tridao / flash-attention-wheels
  ☆48Updated last year
• TiledTensor / TiledBench
  Benchmark tests supporting the TiledCUDA library.
  ☆16Updated 5 months ago
• INT-FlashAttention2024 / INT-FlashAttention
  ☆68Updated 3 months ago
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆69Updated 10 months ago
• glassroom / heinsen_attention
  Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)
  ☆24Updated 11 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆84Updated last week
• Aleph-Alpha / NeurIPS-WANT-submission-efficient-parallelization-layouts
  ☆22Updated last year
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆38Updated last year
• graphcore-research / out-of-the-box-fp8-training
  Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.
  ☆45Updated 9 months ago
• microsoft / AttentionEngine
  ☆68Updated 2 weeks ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆68Updated this week
• BBuf / flash-rwkv
  ☆30Updated 11 months ago
• softmax1 / Flash-Attention-Softmax-N
  CUDA and Triton implementations of Flash Attention with SoftmaxN.
  ☆69Updated 11 months ago
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆60Updated last year
• pytorch-labs / helion
  A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.
  ☆102Updated this week
• sandyresearch / chipmunk
  🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …
  ☆51Updated this week
• sgl-project / DeepGEMM
  DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
  ☆15Updated this week
• 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.
  ☆36Updated last month
• PipeFusion / PipeFusion
  A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters
  ☆45Updated 9 months ago