Code for the EMNLP24 paper "A simple and effective L2 norm based method for KV Cache compression."
☆19Dec 13, 2024Updated last year
Alternatives and similar repositories for l2compress
Users that are interested in l2compress are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official repository of: Attention Sinks in Diffusion Language Models☆12Dec 10, 2025Updated 10 months ago
- ☆10Jul 31, 2025Updated last year
- Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)☆35Mar 7, 2025Updated last year
- [ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Training☆24Aug 18, 2024Updated 2 years ago
- [ICLR'25] Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"☆83Nov 25, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- LongAttn ：Selecting Long-context Training Data via Token-level Attention☆15Jul 16, 2025Updated last year
- [EMNLP 2024 (main)] Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters☆14Nov 5, 2024Updated last year
- PyTorch implementation of StableMask (ICML'24)☆15Jun 27, 2024Updated 2 years ago
- ☆47Nov 25, 2024Updated last year
- ☆21Apr 13, 2024Updated 2 years ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆57Aug 6, 2025Updated last year
- Official Implementation of "DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucination"☆30Dec 18, 2024Updated last year
- ☆11May 24, 2024Updated 2 years ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆88Jun 20, 2026Updated 4 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths☆19Jul 10, 2025Updated last year
- SNp Exploration and Analysis using EPigenomics data☆12Oct 15, 2026Updated 2 weeks ago
- Codebase for Hyperdecoders https://arxiv.org/abs/2203.08304☆14Oct 11, 2022Updated 4 years ago
- ☆11Jun 24, 2024Updated 2 years ago
- Code repo for paper on Generative Adversarial Networks for Medical Imaging☆11Mar 20, 2020Updated 6 years ago
- Marathon: A Multiple-choice Long Context Evaluation Benchmark for Large Language Models.☆10May 16, 2024Updated 2 years ago
- ☆24Feb 14, 2026Updated 8 months ago
- [ACL 2026] Repository of IPBench☆25Apr 6, 2026Updated 6 months ago
- Efficient retrieval head analysis with triton flash attention that supports topK probability☆13Jun 15, 2024Updated 2 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆28Oct 25, 2025Updated last year
- ☆32Feb 3, 2026Updated 9 months ago
- Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals; ACL 2024☆13May 24, 2024Updated 2 years ago
- Official repo of paper LM2☆49Feb 13, 2025Updated last year
- A collection of implementations of fair ML algorithms☆12Jan 7, 2018Updated 8 years ago
- Dataset and baseline for Coling 2022 long paper (oral): "ConFiguRe: Exploring Discourse-level Chinese Figures of Speech"☆12Jul 27, 2023Updated 3 years ago
- War Games measures whether frontier models can sustain long-horizon planning and adaptation in complex, non-stationary real-time games, w…☆15May 5, 2026Updated 5 months ago
- Efficient Memory-Augmented Transformers☆35Dec 5, 2022Updated 3 years ago
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆19Oct 21, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆35Jun 12, 2024Updated 2 years ago
- ☆14Oct 6, 2026Updated 3 weeks ago
- In this lab, you will learn how to use Amazon SageMaker to fine-tune a pretrained Hugging Face LLM using AWS Trainium accelerators, and t…☆12Feb 20, 2024Updated 2 years ago
- ☆12Sep 8, 2023Updated 3 years ago
- ☆13Jul 23, 2024Updated 2 years ago
- Pytorch implementation for "Compressed Context Memory For Online Language Model Interaction" (ICLR'24)☆63Apr 18, 2024Updated 2 years ago
- Rationale-enhanced language models are better continual relation learners (EMNLP 2023 Main Conference)☆12Oct 11, 2023Updated 3 years ago