siyan-zhao / prepacking
The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"
☆59Updated 5 months ago
Alternatives and similar repositories for prepacking:
Users that are interested in prepacking are comparing it to the libraries listed below
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆40Updated last year
- Simple and efficient pytorch-native transformer training and inference (batched)☆69Updated 11 months ago
- This repo is based on https://github.com/jiaweizzhao/GaLore☆26Updated 5 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆58Updated last month
- ☆125Updated last year
- Using FlexAttention to compute attention with different masking patterns☆42Updated 5 months ago
- DPO, but faster 🚀☆40Updated 3 months ago
- ☆94Updated 9 months ago
- Cascade Speculative Drafting☆29Updated 11 months ago
- Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTO…☆53Updated last month
- ☆49Updated 4 months ago
- ☆75Updated last month
- From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients. Ajay Jaiswal, Lu Yin, Zhenyu Zhang, Shiwei Liu,…☆44Updated 7 months ago
- ☆84Updated 5 months ago
- Language models scale reliably with over-training and on downstream tasks☆96Updated 11 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆67Updated 6 months ago
- ☆38Updated 10 months ago
- ☆115Updated 3 weeks ago
- NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference☆64Updated 3 months ago
- ☆43Updated last year
- A repository for research on medium sized language models.☆77Updated 9 months ago
- Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models☆33Updated 3 months ago
- JORA: JAX Tensor-Parallel LoRA Library (ACL 2024)☆32Updated 10 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆121Updated 7 months ago
- Train, tune, and infer Bamba model☆86Updated last month
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆46Updated last year
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆147Updated last month
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆63Updated 7 months ago