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.
☆149Updated last month
Alternatives and similar repositories for LCKV
Users that are interested in LCKV are comparing it to the libraries listed below
Sorting:
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆126Updated 6 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆116Updated 6 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆106Updated 2 months ago
- ☆125Updated last year
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆161Updated 11 months ago
- ☆248Updated last year
- ☆50Updated 7 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆134Updated 9 months ago
- ☆129Updated 3 months ago
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆95Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆59Updated 7 months ago
- ☆79Updated 4 months ago
- Cascade Speculative Drafting☆29Updated last year
- Easy control for Key-Value Constrained Generative LLM Inference(https://arxiv.org/abs/2402.06262)☆63Updated last year
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆234Updated 3 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆186Updated 2 months ago
- The official repo for "LLoCo: Learning Long Contexts Offline"☆116Updated 11 months ago
- This is the official repository for Inheritune.☆111Updated 3 months ago
- ☆45Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆163Updated 10 months ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆84Updated 11 months ago
- The HELMET Benchmark☆149Updated last month
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆155Updated last month
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆62Updated 4 months ago
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆202Updated last year
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆143Updated 8 months ago
- Pytorch implementation for "Compressed Context Memory For Online Language Model Interaction" (ICLR'24)☆60Updated last year
- ☆144Updated 2 years ago
- PB-LLM: Partially Binarized Large Language Models☆152Updated last year
- Official implementation for 'Extending LLMs’ Context Window with 100 Samples'☆78Updated last year