zankner / HydraLinks
☆48Updated last year
Alternatives and similar repositories for Hydra
Users that are interested in Hydra are comparing it to the libraries listed below
Sorting:
- ☆147Updated 9 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆169Updated last year
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆105Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆111Updated 7 months ago
- ☆287Updated 4 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆210Updated 2 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆64Updated last year
- Explorations into some recent techniques surrounding speculative decoding☆290Updated 10 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆61Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆248Updated last month
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆208Updated 9 months ago
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆86Updated 8 months ago
- ☆234Updated last year
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆80Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆85Updated last year
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆48Updated 8 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆217Updated last year
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆21Updated last year
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆26Updated 7 months ago
- ☆130Updated 5 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆175Updated last year
- ☆38Updated last year
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆97Updated 4 months ago
- Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"☆74Updated 4 months ago
- Unofficial implementations of block/layer-wise pruning methods for LLMs.☆72Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆128Updated 2 weeks ago
- The official code for Dropping Backward Propagation (DropBP)☆30Updated last year
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆245Updated 3 months ago
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆95Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆332Updated last month