Alternatives and similar repositories for inference-optimization-blog-post

Users that are interested in inference-optimization-blog-post are comparing it to the libraries listed below

• gpu-mode / profiling-cuda-in-torch
  ☆173Updated last year
• gpu-mode / ring-attention
  ring-attention experiments
  ☆152Updated 11 months ago
• cloneofsimo / min-fsdp
  ☆89Updated last year
• dshah3 / GPU-Puzzles
  Solve puzzles. Learn CUDA.
  ☆63Updated last year
• huggingface / kernels
  Load compute kernels from the Hub
  ☆290Updated last week
• siboehm / ShallowSpeed
  Small scale distributed training of sequential deep learning models, built on Numpy and MPI.
  ☆142Updated last year
• meta-pytorch / float8_experimental
  This repository contains the experimental PyTorch native float8 training UX
  ☆224Updated last year
• gau-nernst / learn-cuda
  Learn CUDA with PyTorch
  ☆84Updated last week
• MekkCyber / TritonAcademy
  A repository to unravel the language of GPUs, making their kernel conversations easy to understand
  ☆193Updated 4 months ago
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆81Updated last year
• IST-DASLab / llmq
  Quantized LLM training in pure CUDA/C++.
  ☆32Updated this week
• cloneofsimo / ptx-tutorial-by-aislop
  PTX-Tutorial Written Purely By AIs (Deep Research of Openai and Claude 3.7)
  ☆66Updated 6 months ago
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆130Updated 10 months ago
• mobiusml / gemlite
  Fast low-bit matmul kernels in Triton
  ☆373Updated last week
• nshepperd / flash_attn_jax
  JAX bindings for Flash Attention v2
  ☆92Updated 3 weeks ago
• foundation-model-stack / fms-fsdp
  🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…
  ☆268Updated 2 months ago
• open-lm-engine / flash-model-architectures
  A bunch of kernels that might make stuff slower 😉
  ☆59Updated this week
• huggingface / kernel-builder
  👷 Build compute kernels
  ☆149Updated this week
• MatX-inc / seqax
  seqax = sequence modeling + JAX
  ☆167Updated 2 months ago
• gpu-mode / triton-index
  Cataloging released Triton kernels.
  ☆261Updated 3 weeks ago
• linjames0 / Transformer-CUDA
  An implementation of the transformer architecture onto an Nvidia CUDA kernel
  ☆190Updated 2 years ago
• gpu-mode / discord-cluster-manager
  Write a fast kernel and run it on Discord. See how you compare against the best!
  ☆57Updated this week
• Deep-Learning-Profiling-Tools / triton-viz
  ☆240Updated this week
• unixpickle / learn-ptx
  Learning about CUDA by writing PTX code.
  ☆137Updated last year
• huggingface / picotron_tutorial
  ☆221Updated 7 months ago
• BobMcDear / attorch
  A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
  ☆576Updated last month
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• mgmalek / efficient_cross_entropy
  ☆122Updated last year
• hyhieu / easy_pybind
  ☆32Updated last year
• salykova / sgemm.cu
  High-Performance SGEMM on CUDA devices
  ☆103Updated 8 months ago