kssteven418 / BigLittleDecoderLinks
[NeurIPS'23] Speculative Decoding with Big Little Decoder
☆95Updated last year
Alternatives and similar repositories for BigLittleDecoder
Users that are interested in BigLittleDecoder are comparing it to the libraries listed below
Sorting:
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆21Updated last year
- Explorations into some recent techniques surrounding speculative decoding☆295Updated last year
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆65Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆172Updated last year
- [KDD'22] Learned Token Pruning for Transformers☆102Updated 2 years ago
- Repository of the paper "Accelerating Transformer Inference for Translation via Parallel Decoding"☆121Updated last year
- ☆62Updated 2 years ago
- ☆155Updated 10 months ago
- ☆150Updated 2 years ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆219Updated last year
- ☆39Updated last year
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆98Updated 2 years ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆112Updated 9 months ago
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆26Updated 8 months ago
- Code for ACL2022 publication Transkimmer: Transformer Learns to Layer-wise Skim☆22Updated 3 years ago
- ☆115Updated last year
- [NeurIPS 2022] A Fast Post-Training Pruning Framework for Transformers☆192Updated 2 years ago
- ☆157Updated 2 years ago
- ☆31Updated last year
- ☆48Updated last year
- ☆53Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆89Updated last year
- ☆83Updated 2 years ago
- Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"☆74Updated 5 months ago
- Efficient LLM Inference Acceleration using Prompting☆51Updated last year
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆43Updated last year
- ☆221Updated 2 years ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆82Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆257Updated 2 months ago
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆87Updated 9 months ago