Alternatives and similar repositories for prepacking:

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

• IST-DASLab / SparseFinetuning
  Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry
  ☆40Updated last year
• Edward-Sun / gpt-accelera
  Simple and efficient pytorch-native transformer training and inference (batched)
  ☆73Updated last year
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆43Updated 7 months ago
• PiotrNawrot / nano-sparse-attention
  The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
  ☆60Updated 3 months ago
• HanGuo97 / lq-lora
  ☆125Updated last year
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆126Updated 5 months ago
• whyNLP / LCKV
  Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…
  ☆148Updated 3 weeks ago
• wdlctc / mini-s
  ☆50Updated 6 months ago
• kyleliang919 / Online-Subspace-Descent
  This repo is based on https://github.com/jiaweizzhao/GaLore
  ☆27Updated 7 months ago
• Infini-AI-Lab / gsm_infinite
  ☆44Updated 2 months ago
• mlfoundations / scaling
  Language models scale reliably with over-training and on downstream tasks
  ☆96Updated last year
• ServiceNow / PipelineRL
  A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
  ☆94Updated this week
• mnoukhov / async_rlhf
  Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models
  ☆48Updated last week
• SalesforceAIResearch / GemFilter
  ☆77Updated 3 months ago
• microsoft / mutransformers
  some common Huggingface transformers in maximal update parametrization (µP)
  ☆80Updated 3 years ago
• nil0x9 / flash-muon
  Flash-Muon: An Efficient Implementation of Muon Optimzer
  ☆91Updated this week
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆115Updated 5 months ago
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆73Updated 8 months ago
• huggingface / kernels
  Load compute kernels from the Hub
  ☆115Updated last week
• RobertCsordas / moeut
  ☆78Updated 8 months ago
• google-deepmind / asyncdiloco
  ☆43Updated last year
• FasterDecoding / TEAL
  ☆126Updated 2 months ago
• mgmalek / efficient_cross_entropy
  ☆103Updated 11 months ago
• kyegomez / Infini-attention
  Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTO…
  ☆55Updated 2 weeks ago
• IST-DASLab / QuEST
  Work in progress.
  ☆58Updated 3 weeks ago
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆103Updated last month
• frankxwang / dpo-prefix-sharing
  DPO, but faster 🚀
  ☆41Updated 5 months ago
• IST-DASLab / MoE-Quant
  Code for data-aware compression of DeepSeek models
  ☆21Updated 3 weeks ago
• sail-sg / SkyLadder
  The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling
  ☆29Updated last month
• snu-mllab / Context-Memory
  Pytorch implementation for "Compressed Context Memory For Online Language Model Interaction" (ICLR'24)
  ☆59Updated last year