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
  ☆42Updated last year
• PiotrNawrot / nano-sparse-attention
  The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
  ☆91Updated 5 months ago
• PiotrNawrot / sparse-frontier
  The evaluation framework for training-free sparse attention in LLMs
  ☆106Updated 2 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…
  ☆157Updated 8 months ago
• TRI-ML / linear_open_lm
  A repository for research on medium sized language models.
  ☆77Updated last year
• HanGuo97 / lq-lora
  ☆128Updated last year
• wdlctc / mini-s
  ☆54Updated last year
• jeffreysijuntan / lloco
  The official repo for "LLoCo: Learning Long Contexts Offline"
  ☆118Updated last year
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆131Updated last year
• SalesforceAIResearch / GemFilter
  ☆85Updated last month
• Edward-Sun / gpt-accelera
  Simple and efficient pytorch-native transformer training and inference (batched)
  ☆79Updated last year
• frankxwang / dpo-prefix-sharing
  DPO, but faster 🚀
  ☆46Updated last year
• kyegomez / Infini-attention
  Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTO…
  ☆58Updated 3 weeks ago
• mlfoundations / scaling
  Language models scale reliably with over-training and on downstream tasks
  ☆100Updated last year
• VITA-Group / WeLore
  [ICML 2025] From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories and Applications
  ☆52Updated last month
• FasterDecoding / BitDelta
  ☆204Updated last year
• kyleliang919 / Online-Subspace-Descent
  [NeurIPS 2024] Low rank memory efficient optimizer without SVD
  ☆32Updated 5 months ago
• Infini-AI-Lab / gsm_infinite
  ☆60Updated 6 months ago
• google-deepmind / asyncdiloco
  ☆47Updated last year
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆86Updated last year
• RobertCsordas / moeut
  ☆91Updated last year
• sail-sg / SkyLadder
  The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling
  ☆40Updated 2 months ago
• minyoungg / LTE
  ☆71Updated last year
• softmax1 / Flash-Attention-Softmax-N
  CUDA and Triton implementations of Flash Attention with SoftmaxN.
  ☆73Updated last year
• microsoft / mutransformers
  some common Huggingface transformers in maximal update parametrization (µP)
  ☆87Updated 3 years ago
• lfsszd / CS-Drafting
  Cascade Speculative Drafting
  ☆32Updated last year
• AnswerDotAI / cold-compress
  Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…
  ☆146Updated last year
• SeunghyunSEO / optimized_hf_llama_class_for_training
  ☆48Updated last year
• snu-mllab / Context-Memory
  Pytorch implementation for "Compressed Context Memory For Online Language Model Interaction" (ICLR'24)
  ☆62Updated last year
• IST-DASLab / RoSA
  Official implementation of the ICML 2024 paper RoSA (Robust Adaptation)
  ☆44Updated last year