Alternatives and similar repositories for paged-attention-minimal:

Users that are interested in paged-attention-minimal are comparing it to the libraries listed below

• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆106Updated 9 months ago
• ColfaxResearch / cutlass-kernels
  ☆202Updated 9 months ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆88Updated last week
• pytorch-labs / tritonbench
  Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.
  ☆122Updated this week
• triton-lang / kernels
  ☆79Updated 6 months ago
• gpu-mode / triton-index
  Cataloging released Triton kernels.
  ☆220Updated 4 months ago
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆206Updated last year
• SqueezeBits / QUICK
  QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
  ☆117Updated last year
• AlibabaPAI / FLASHNN
  ☆93Updated 8 months ago
• INT-FlashAttention2024 / INT-FlashAttention
  ☆68Updated 3 months ago
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆308Updated 10 months ago
• mobiusml / gemlite
  Fast low-bit matmul kernels in Triton
  ☆297Updated this week
• pytorch-labs / applied-ai
  Applied AI experiments and examples for PyTorch
  ☆264Updated last week
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆73Updated 8 months ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆69Updated this week
• InternLM / turbomind
  ☆84Updated last month
• NVIDIA / online-softmax
  Benchmark code for the "Online normalizer calculation for softmax" paper
  ☆91Updated 6 years ago
• Deep-Learning-Profiling-Tools / triton-viz
  ☆202Updated 2 weeks ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆67Updated last week
• microsoft / SparTA
  ☆143Updated 9 months ago
• MDK8888 / vllmini
  A minimal implementation of vllm.
  ☆40Updated 9 months ago
• stanford-futuredata / stk
  ☆104Updated 8 months ago
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆266Updated 11 months ago
• efeslab / fiddler
  [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
  ☆209Updated 5 months ago
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆82Updated 4 months ago
• cchan / tccl
  extensible collectives library in triton
  ☆86Updated last month
• mayank31398 / cute-kernels
  A bunch of kernels that might make stuff slower 😉
  ☆40Updated this week
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆54Updated 3 months ago
• gpu-mode / ring-attention
  ring-attention experiments
  ☆140Updated 6 months ago
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆248Updated 6 months ago