Alternatives and similar repositories for mixed-precision-from-scratch

Users that are interested in mixed-precision-from-scratch are comparing it to the libraries listed below

• PiotrNawrot / nano-sparse-attention
  The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
  ☆89Updated 2 months ago
• gpu-mode / profiling-cuda-in-torch
  ☆173Updated last year
• gau-nernst / learn-cuda
  Learn CUDA with PyTorch
  ☆85Updated 2 weeks ago
• PiotrNawrot / sparse-frontier
  The evaluation framework for training-free sparse attention in LLMs
  ☆101Updated 3 months ago
• meta-pytorch / float8_experimental
  This repository contains the experimental PyTorch native float8 training UX
  ☆223Updated last year
• gpu-mode / ring-attention
  ring-attention experiments
  ☆153Updated 11 months ago
• huggingface / kernels
  Load compute kernels from the Hub
  ☆299Updated this week
• Dao-AILab / grouped-latent-attention
  ☆129Updated 4 months ago
• mgmalek / efficient_cross_entropy
  ☆120Updated last year
• gpu-mode / triton-index
  Cataloging released Triton kernels.
  ☆261Updated last month
• shawntan / scattermoe
  Triton-based implementation of Sparse Mixture of Experts.
  ☆244Updated last week
• zinccat / Awesome-Triton-Kernels
  Collection of kernels written in Triton language
  ☆157Updated 6 months ago
• mengxiayu / LLMSuperWeight
  Code for studying the super weight in LLM
  ☆120Updated 10 months ago
• IST-DASLab / qutlass
  QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning
  ☆114Updated last week
• AnswerDotAI / cold-compress
  Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…
  ☆147Updated last year
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆80Updated last year
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆168Updated last year
• FasterDecoding / TEAL
  ☆143Updated 7 months ago
• mobiusml / gemlite
  Fast low-bit matmul kernels in Triton
  ☆379Updated 2 weeks ago
• tspeterkim / paged-attention-minimal
  a minimal cache manager for PagedAttention, on top of llama3.
  ☆123Updated last year
• siboehm / ShallowSpeed
  Small scale distributed training of sequential deep learning models, built on Numpy and MPI.
  ☆144Updated last year
• open-lm-engine / flash-model-architectures
  A bunch of kernels that might make stuff slower 😉
  ☆61Updated this week
• Deep-Learning-Profiling-Tools / triton-viz
  ☆242Updated this week
• meta-pytorch / applied-ai
  Applied AI experiments and examples for PyTorch
  ☆296Updated last month
• nil0x9 / flash-muon
  Flash-Muon: An Efficient Implementation of Muon Optimizer
  ☆193Updated 3 months ago
• kyegomez / FlashAttention20
  Get down and dirty with FlashAttention2.0 in pytorch, plug in and play no complex CUDA kernels
  ☆108Updated 2 years ago
• stanford-futuredata / stk
  ☆112Updated last year
• vdesai2014 / inference-optimization-blog-post
  ☆89Updated last year
• IST-DASLab / Quartet
  ☆100Updated last month
• fw-ai / llama-cuda-graph-example
  Example of applying CUDA graphs to LLaMA-v2
  ☆12Updated 2 years ago