VITA-Group / LoCoCoLinks
[ICML‘2024] "LoCoCo: Dropping In Convolutions for Long Context Compression", Ruisi Cai, Yuandong Tian, Zhangyang Wang, Beidi Chen
☆16Updated 8 months ago
Alternatives and similar repositories for LoCoCo
Users that are interested in LoCoCo are comparing it to the libraries listed below
Sorting:
- [NAACL 2025] A Closer Look into Mixture-of-Experts in Large Language Models☆52Updated 3 months ago
- Code for the EMNLP24 paper "A simple and effective L2 norm based method for KV Cache compression."☆13Updated 5 months ago
- [ICML2024 Spotlight] Fine-Tuning Pre-trained Large Language Models Sparsely☆23Updated 11 months ago
- [ICML 2024] Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity; Lu Yin*, Ajay Jaiswal*, Shiwei Liu, So…☆16Updated last month
- Code for "Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes"☆28Updated last year
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆49Updated 3 months ago
- Repo for ACL2023 Findings paper "Emergent Modularity in Pre-trained Transformers"☆23Updated last year
- A Sober Look at Language Model Reasoning☆52Updated this week
- Long Context Extension and Generalization in LLMs☆56Updated 8 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆60Updated 8 months ago
- The official implementation for Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free☆38Updated 3 weeks ago
- ☆19Updated 3 months ago
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆78Updated 2 weeks ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆32Updated 2 months ago
- Beyond KV Caching: Shared Attention for Efficient LLMs☆19Updated 10 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆45Updated 7 months ago
- ☆37Updated 9 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
- [EMNLP 2023]Context Compression for Auto-regressive Transformers with Sentinel Tokens☆24Updated last year
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆38Updated 9 months ago
- Code for "RSQ: Learning from Important Tokens Leads to Better Quantized LLMs"☆17Updated 2 weeks ago
- Easy control for Key-Value Constrained Generative LLM Inference(https://arxiv.org/abs/2402.06262)☆63Updated last year
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆38Updated last year
- [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…☆51Updated 2 years ago
- ☆79Updated 4 months ago
- ☆28Updated last month
- ☆47Updated 2 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆46Updated 7 months ago
- ☆83Updated last month
- ☆56Updated last year