Alternatives and similar repositories for kernels

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

• foundation-model-stack / fms-fsdp
  🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…
  ☆270Updated 2 months ago
• huggingface / kernel-builder
  👷 Build compute kernels
  ☆163Updated this week
• huggingface / picotron_tutorial
  ☆222Updated 3 weeks ago
• changjonathanc / flex-nano-vllm
  FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.
  ☆296Updated 2 months ago
• meta-pytorch / torchft
  Fault tolerance for PyTorch (HSDP, LocalSGD, DiLoCo, Streaming DiLoCo)
  ☆420Updated this week
• meta-pytorch / float8_experimental
  This repository contains the experimental PyTorch native float8 training UX
  ☆223Updated last year
• mgmalek / efficient_cross_entropy
  ☆121Updated last year
• nil0x9 / flash-muon
  Flash-Muon: An Efficient Implementation of Muon Optimizer
  ☆195Updated 4 months ago
• MekkCyber / TritonAcademy
  A repository to unravel the language of GPUs, making their kernel conversations easy to understand
  ☆193Updated 4 months ago
• shawntan / scattermoe
  Triton-based implementation of Sparse Mixture of Experts.
  ☆246Updated 3 weeks ago
• foundation-model-stack / foundation-model-stack
  🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.
  ☆215Updated this week
• gpu-mode / ring-attention
  ring-attention experiments
  ☆154Updated last year
• mobiusml / gemlite
  Fast low-bit matmul kernels in Triton
  ☆381Updated 3 weeks ago
• vllm-project / compressed-tensors
  A safetensors extension to efficiently store sparse quantized tensors on disk
  ☆180Updated this week
• NVIDIA / Star-Attention
  Efficient LLM Inference over Long Sequences
  ☆390Updated 3 months ago
• meta-pytorch / applied-ai
  Applied AI experiments and examples for PyTorch
  ☆299Updated 2 months ago
• gpu-mode / profiling-cuda-in-torch
  ☆174Updated last year
• facebookresearch / LayerSkip
  Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024
  ☆344Updated 5 months ago
• gpu-mode / triton-index
  Cataloging released Triton kernels.
  ☆263Updated last month
• apple / ml-cross-entropy
  ☆534Updated last month
• HazyResearch / lolcats
  Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"
  ☆248Updated 8 months ago
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆192Updated 11 months ago
• wolfecameron / nanoMoE
  An extension of the nanoGPT repository for training small MOE models.
  ☆202Updated 7 months ago
• BobMcDear / attorch
  A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
  ☆578Updated 2 months ago
• PiotrNawrot / nano-sparse-attention
  The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
  ☆91Updated 3 months ago
• Deep-Learning-Profiling-Tools / triton-viz
  ☆240Updated this week
• NVIDIA / kvpress
  LLM KV cache compression made easy
  ☆660Updated last week
• NVIDIA-NeMo / Automodel
  Pytorch DTensor native training library for LLMs/VLMs with OOTB Hugging Face support
  ☆135Updated this week
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆130Updated 10 months ago
• facebookresearch / spdl
  Scalable and Performant Data Loading
  ☆311Updated this week