pan-x-c / EE-LLM
EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).
☆53Updated 8 months ago
Alternatives and similar repositories for EE-LLM:
Users that are interested in EE-LLM are comparing it to the libraries listed below
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆107Updated 2 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆157Updated 7 months ago
- ☆111Updated this week
- ☆36Updated 5 months ago
- Unofficial implementations of block/layer-wise pruning methods for LLMs.☆62Updated 9 months ago
- The official implementation of the paper "Demystifying the Compression of Mixture-of-Experts Through a Unified Framework".☆59Updated 3 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆48Updated 7 months ago
- Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks☆33Updated 2 weeks ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆145Updated 8 months ago
- ☆41Updated 2 months ago
- ☆220Updated 9 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆84Updated 4 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆56Updated 3 months ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆72Updated 8 months ago
- An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆35Updated 8 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆56Updated 4 months ago
- Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆78Updated 2 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆81Updated last year
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆51Updated last week
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆33Updated 6 months ago
- 16-fold memory access reduction with nearly no loss☆77Updated this week
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆223Updated 3 months ago
- Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"☆57Updated 7 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆160Updated last week
- Explorations into some recent techniques surrounding speculative decoding☆240Updated last month
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆82Updated 8 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆64Updated 5 months ago
- ☆49Updated 9 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆272Updated last month