Multi-Candidate Speculative Decoding
☆41Apr 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:
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆117Mar 20, 2025Updated last year
- ☆28Mar 14, 2024Updated 2 years ago
- Cascade Speculative Drafting☆32Apr 2, 2024Updated 2 years ago
- official code for GliDe with a CaPE☆21Aug 13, 2024Updated 2 years ago
- Explorations into some recent techniques surrounding speculative decoding☆308Dec 22, 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.
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆231Feb 13, 2025Updated last year
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆415Apr 22, 2025Updated last year
- (COLING2025) SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding☆10Dec 18, 2024Updated last year
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆99Feb 6, 2024Updated 2 years ago
- ☆16Aug 19, 2024Updated 2 years ago
- ☆68Dec 3, 2024Updated last year
- Accepted by NAACL 2025 main conference.☆11Jan 24, 2025Updated last year
- Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths☆19Jul 10, 2025Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆175Dec 23, 2025Updated 10 months ago
- 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.
- The fastest off-the-shelf inference algorithm for LLMs (ICLR’25)☆14Mar 8, 2025Updated last year
- ☆11Feb 5, 2026Updated 9 months ago
- NJUQE is an open-source toolkit to build machine translation quality estimation models.☆12Sep 10, 2025Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,579Feb 20, 2026Updated 8 months ago
- ☆22Dec 11, 2024Updated last year
- [ACL 2024] Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"☆46May 24, 2024Updated 2 years ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆67Sep 28, 2024Updated 2 years ago
- ☆12May 19, 2025Updated last year
- This repository contains papers for a comprehensive survey on accelerated generation techniques in Large Language Models (LLMs).☆11May 24, 2024Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆280Aug 31, 2024Updated 2 years ago
- Official implementation of SPACE☆10May 19, 2024Updated 2 years ago
- Implementation of "Decoding-time Realignment of Language Models", ICML 2024.☆21Jun 17, 2024Updated 2 years ago
- The official implementation of the DAC 2024 paper GQA-LUT☆26Dec 20, 2024Updated last year
- ☆14Aug 14, 2025Updated last year
- Code for ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context☆17Nov 15, 2024Updated 2 years ago
- [ICCV'2025 Highlight] Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation☆10Mar 30, 2026Updated 7 months ago
- ☆11Mar 14, 2024Updated 2 years ago
- ☆15Dec 8, 2025Updated 11 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.
- Continuous Pipelined Speculative Decoding☆22May 25, 2026Updated 5 months ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,776Jun 25, 2024Updated 2 years ago
- [ICML 2025] AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism☆20Jul 14, 2025Updated last year
- scalable and robust tree-based speculative decoding algorithm☆376Jan 28, 2025Updated last year
- ☆365Apr 2, 2024Updated 2 years ago
- ☆13May 11, 2023Updated 3 years ago
- This is the public repo for DREAM accepted to ICS 2025.☆12Dec 28, 2025Updated 10 months ago
Are these results useful?