kyegomez / Speculative-Decoding
My own implementation of "Fast Inference from Transformers via Speculative Decoding"
☆11Updated 11 months ago
Related projects ⓘ
Alternatives and complementary repositories for Speculative-Decoding
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆52Updated last month
- SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆22Updated last month
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆19Updated 2 months ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆64Updated 5 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆32Updated 2 months ago
- Code for "Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes"☆28Updated 7 months ago
- ☆31Updated 2 months ago
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆75Updated last month
- ☆121Updated 9 months ago
- Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks☆30Updated 4 months ago
- Multi-Candidate Speculative Decoding☆28Updated 6 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆76Updated last month
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆36Updated 3 weeks ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆113Updated last week
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆34Updated 7 months ago
- ☆62Updated last month
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆137Updated this week
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆49Updated 3 weeks ago
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning"☆91Updated 4 months ago
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆70Updated last week
- Official PyTorch implementation of DistiLLM: Towards Streamlined Distillation for Large Language Models (ICML 2024)☆134Updated last month
- Long Context Extension and Generalization in LLMs☆39Updated last month
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆96Updated 7 months ago
- Unofficial implementations of block/layer-wise pruning methods for LLMs.☆49Updated 6 months ago
- ☆31Updated 2 months ago
- The official implementation of the paper "Demystifying the Compression of Mixture-of-Experts Through a Unified Framework".☆48Updated 2 weeks ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆21Updated 4 months ago
- Cascade Speculative Drafting☆26Updated 7 months ago
- OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure☆18Updated 3 months ago
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆47Updated 4 months ago