lucidrains / speculative-decoding
Explorations into some recent techniques surrounding speculative decoding
☆250Updated 3 months ago
Alternatives and similar repositories for speculative-decoding:
Users that are interested in speculative-decoding are comparing it to the libraries listed below
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆198Updated 4 months ago
- ☆233Updated 11 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆245Updated last week
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆177Updated last month
- ☆220Updated 9 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆284Updated 2 months ago
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆91Updated last year
- Official PyTorch implementation of QA-LoRA☆129Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆209Updated 4 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆155Updated 9 months ago
- ☆311Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆301Updated 9 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆337Updated 7 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆207Updated 7 months ago
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆92Updated last year
- Official PyTorch implementation of DistiLLM: Towards Streamlined Distillation for Large Language Models (ICML 2024)☆203Updated 2 weeks ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆433Updated 8 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆265Updated 4 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆124Updated 7 months ago
- ☆43Updated last year
- ☆122Updated last month
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆158Updated 8 months ago
- Code for studying the super weight in LLM☆94Updated 3 months ago
- ☆195Updated 3 months ago
- ☆125Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆90Updated last week
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆368Updated 4 months ago
- A family of compressed models obtained via pruning and knowledge distillation☆331Updated 4 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆234Updated this week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆111Updated 3 months ago