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
- Fast inference from large lauguage models via speculative decoding☆927Aug 22, 2024Updated 2 years ago
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,305Jun 27, 2026Updated 4 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆220Mar 5, 2026Updated 7 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆415Apr 22, 2025Updated last year
- 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.
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆67Sep 28, 2024Updated 2 years ago
- 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…☆74Jun 26, 2024Updated 2 years ago
- Explorations into some recent techniques surrounding speculative decoding☆308Dec 22, 2024Updated last year
- ☆55Feb 19, 2024Updated 2 years ago
- Official implementation of SPACE☆10May 19, 2024Updated 2 years ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,774Jun 25, 2024Updated 2 years ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,568Feb 20, 2026Updated 8 months ago
- ☆363Apr 2, 2024Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆379Jul 20, 2026Updated 3 months ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆280Aug 31, 2024Updated 2 years ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,345Mar 6, 2025Updated last year
- [ICLR 2025] Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models☆75Mar 29, 2025Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆161Dec 4, 2024Updated last year
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆99Feb 6, 2024Updated 2 years ago
- Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning☆59Mar 26, 2024Updated 2 years ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆117Mar 20, 2025Updated last year
- ☆71Nov 4, 2024Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆98Aug 20, 2023Updated 3 years ago
- scalable and robust tree-based speculative decoding algorithm☆375Jan 28, 2025Updated last year
- The Official Implementation of Ada-KV [NeurIPS 2025]☆143Nov 26, 2025Updated 11 months ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,903Updated this week
- ☆11Feb 5, 2026Updated 8 months ago
- Official implementation of the paper: "A deeper look at depth pruning of LLMs"☆15Jul 24, 2024Updated 2 years ago
- Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)☆47Dec 9, 2023Updated 2 years ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆537Aug 1, 2024Updated 2 years ago
- ☆20Dec 24, 2024Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆56Mar 14, 2025Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆173Dec 23, 2025Updated 10 months ago
- ☆336Jul 10, 2025Updated last year
- contrastive decoding☆207Nov 14, 2022Updated 3 years ago
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆316May 1, 2025Updated last year
- Cascade Speculative Drafting☆33Apr 2, 2024Updated 2 years ago
- [EMNLP 2025 Main] SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning☆50Apr 16, 2026Updated 6 months ago