Infini-AI-Lab / SiriusLinks
Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its efficiency gain.
☆22Updated 10 months ago
Alternatives and similar repositories for Sirius
Users that are interested in Sirius are comparing it to the libraries listed below
Sorting:
- ☆137Updated 5 months ago
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆93Updated last year
- ☆37Updated 2 months ago
- 16-fold memory access reduction with nearly no loss☆103Updated 4 months ago
- ☆27Updated 8 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆44Updated 3 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆50Updated 8 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆48Updated 9 months ago
- ☆50Updated last year
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆81Updated 5 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆128Updated 5 months ago
- ☆47Updated last year
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆61Updated 3 weeks ago
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆26Updated 3 months ago
- ☆38Updated 11 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆42Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 11 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆38Updated 11 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆74Updated 9 months ago
- ☆268Updated 3 weeks ago
- Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"☆73Updated last month
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆72Updated 4 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆109Updated 4 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆230Updated 8 months ago
- ☆54Updated 8 months ago
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆48Updated last month
- TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators☆70Updated last month
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆61Updated 10 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆59Updated last year