lucidrains / speculative-decodingLinks
Explorations into some recent techniques surrounding speculative decoding
☆296Updated last year
Alternatives and similar repositories for speculative-decoding
Users that are interested in speculative-decoding are comparing it to the libraries listed below
Sorting:
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆213Updated 4 months ago
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆106Updated last year
- ☆299Updated 6 months ago
- ☆235Updated last year
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆350Updated 8 months ago
- Official PyTorch implementation of DistiLLM: Towards Streamlined Distillation for Large Language Models (ICML 2024)☆248Updated 10 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆176Updated last year
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆397Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆259Updated 3 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆346Updated last month
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆216Updated 11 months ago
- ☆352Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆220Updated last year
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆99Updated 2 years ago
- ☆49Updated last year
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆500Updated last year
- ☆156Updated 11 months ago
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆96Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆175Updated last year
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆65Updated last year
- Official PyTorch implementation of QA-LoRA☆143Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆146Updated last year
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆88Updated 10 months ago
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆52Updated 10 months ago
- Code for studying the super weight in LLM☆120Updated last year
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆73Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆364Updated 6 months ago
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆322Updated 10 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆278Updated last month
- For releasing code related to compression methods for transformers, accompanying our publications☆454Updated 11 months ago