Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
☆230Feb 13, 2025Updated last year
Alternatives and similar repositories for self-speculative-decoding
Users that are interested in self-speculative-decoding are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆70Feb 21, 2025Updated last year
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆220Mar 5, 2026Updated 4 months ago
- Fast inference from large lauguage models via speculative decoding☆922Aug 22, 2024Updated last year
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆401Apr 22, 2025Updated last year
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,281Jun 27, 2026Updated 3 weeks ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Multi-Candidate Speculative Decoding☆41Apr 22, 2024Updated 2 years ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆72Jun 26, 2024Updated 2 years ago
- Explorations into some recent techniques surrounding speculative decoding☆307Dec 22, 2024Updated last year
- [ICLR 2025] Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models☆75Mar 29, 2025Updated last year
- ☆55Feb 19, 2024Updated 2 years ago
- ☆359Apr 2, 2024Updated 2 years ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,758Jun 25, 2024Updated 2 years ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆67Sep 28, 2024Updated last year
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆99Feb 6, 2024Updated 2 years ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆281Aug 31, 2024Updated last year
- ☆68Nov 4, 2024Updated last year
- scalable and robust tree-based speculative decoding algorithm☆376Jan 28, 2025Updated last year
- Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)☆47Dec 9, 2023Updated 2 years ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,478Feb 20, 2026Updated 5 months ago
- Official implementation of the paper: "A deeper look at depth pruning of LLMs"☆15Jul 24, 2024Updated 2 years ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆117Mar 20, 2025Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,340Mar 6, 2025Updated last year
- ☆11Feb 5, 2026Updated 5 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,898Updated this week
- Rookie's guide☆14Aug 10, 2024Updated last year
- Cascade Speculative Drafting☆33Apr 2, 2024Updated 2 years ago
- Official Implementation of ACL2023: Don't Parse, Choose Spans! Continuous and Discontinuous Constituency Parsing via Autoregressive Span …☆14Aug 25, 2023Updated 2 years ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆372Updated this week
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆99Aug 20, 2023Updated 2 years ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆56Oct 29, 2024Updated last year
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆530Aug 1, 2024Updated last year
- [EMNLP 2025 Main] SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning☆48Apr 16, 2026Updated 3 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆20Dec 24, 2024Updated last year
- Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning☆57Mar 26, 2024Updated 2 years ago
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆56Mar 14, 2025Updated last year
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆29Apr 15, 2025Updated last year
- ☆167Feb 15, 2025Updated last year
- [ACL 2026 Findings] Living repository for the survey paper “Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques…☆26Apr 8, 2026Updated 3 months ago
- Simple speculative decoding technique, integrated in vLLM and transformers☆611Aug 23, 2024Updated last year