Multi-Candidate Speculative Decoding
☆40Apr 22, 2024Updated 2 years ago
Alternatives and similar repositories for MCSD
Users that are interested in MCSD are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Cascade Speculative Drafting☆33Apr 2, 2024Updated 2 years ago
- ☆26Mar 14, 2024Updated 2 years ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆389Apr 22, 2025Updated last year
- Explorations into some recent techniques surrounding speculative decoding☆300Dec 22, 2024Updated last year
- ☆16Aug 19, 2024Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Fast inference from large lauguage models via speculative decoding☆914Aug 22, 2024Updated last year
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆218Mar 5, 2026Updated last month
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆116Mar 20, 2025Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆226Feb 13, 2025Updated last year
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,204Apr 18, 2026Updated last week
- [ACL 2024] Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"☆45May 24, 2024Updated last year
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆97Feb 6, 2024Updated 2 years ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,299Feb 20, 2026Updated 2 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆65Sep 28, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆28Apr 15, 2025Updated last year
- ☆68Nov 4, 2024Updated last year
- This repository contains papers for a comprehensive survey on accelerated generation techniques in Large Language Models (LLMs).☆11May 24, 2024Updated last year
- Implementation of "Decoding-time Realignment of Language Models", ICML 2024.☆21Jun 17, 2024Updated last year
- ☆14May 9, 2024Updated last year
- Code for ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context☆17Nov 15, 2024Updated last year
- [ICML 2025] Official implementation of the paper "SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling". …☆22Nov 17, 2025Updated 5 months ago
- scalable and robust tree-based speculative decoding algorithm☆377Jan 28, 2025Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆273Oct 3, 2025Updated 6 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,727Jun 25, 2024Updated last year
- ☆355Apr 2, 2024Updated 2 years ago
- ☆42Mar 28, 2024Updated 2 years ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆54Oct 29, 2024Updated last year
- ☆66Dec 3, 2024Updated last year
- ☆13Oct 13, 2025Updated 6 months ago
- Code for paper "ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection" (MobiSys'23)☆14Nov 1, 2023Updated 2 years ago
- Lyra: A Benchmark for Turducken-Style Code Generation☆15Apr 22, 2022Updated 4 years ago
- [EMNLP'24] LongHeads: Multi-Head Attention is Secretly a Long Context Processor☆31Apr 8, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆15Apr 11, 2024Updated 2 years ago
- High-performance GEMM implementation optimized for NVIDIA H100 GPUs, leveraging Hopper architecture's TMA, WGMMA, and Thread Block Cluste…☆10Dec 4, 2024Updated last year
- Conic10K: A large-scale dataset for closed-vocabulary math problem understanding. Accepted to EMNLP2023 Findings.☆33Dec 6, 2023Updated 2 years ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆68Jun 26, 2024Updated last year
- [NeurIPS 2024] HonestLLM: Toward an Honest and Helpful Large Language Model☆29Jun 10, 2025Updated 10 months ago
- Tutorial Exercises and Code for GPU Communications Tutorial at HOT Interconnects 2025☆31Oct 22, 2025Updated 6 months ago
- ☆235Jun 11, 2024Updated last year