whyNLP / LCKVLinks
Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance. Accepted to ACL 2024.
☆151Updated 4 months ago
Alternatives and similar repositories for LCKV
Users that are interested in LCKV are comparing it to the libraries listed below
Sorting:
- ☆127Updated last year
- ☆85Updated 7 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆109Updated 5 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆61Updated 10 months ago
- Easy control for Key-Value Constrained Generative LLM Inference(https://arxiv.org/abs/2402.06262)☆63Updated last year
- The official repo for "LLoCo: Learning Long Contexts Offline"☆118Updated last year
- ☆201Updated 8 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆141Updated last year
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆206Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆128Updated 8 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆84Updated last month
- ☆51Updated 9 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆169Updated last year
- ☆139Updated 6 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆240Updated 2 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆124Updated 8 months ago
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆160Updated 4 months ago
- [NeurIPS 2024] Low rank memory efficient optimizer without SVD☆30Updated last month
- Long Context Extension and Generalization in LLMs☆58Updated 11 months ago
- Code for studying the super weight in LLM☆115Updated 8 months ago
- Experiments on speculative sampling with Llama models☆128Updated 2 years ago
- Cascade Speculative Drafting☆29Updated last year
- ☆273Updated last month
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆91Updated 2 months ago
- The HELMET Benchmark☆165Updated last week
- The evaluation framework for training-free sparse attention in LLMs☆90Updated 2 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- Pytorch implementation for "Compressed Context Memory For Online Language Model Interaction" (ICLR'24)☆61Updated last year
- ☆51Updated 2 months ago
- Implementation of NAACL 2024 Outstanding Paper "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"☆148Updated 5 months ago