[NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting"
☆68Jun 26, 2024Updated last year
Alternatives and similar repositories for Kangaroo
Users that are interested in Kangaroo are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆53Feb 19, 2024Updated 2 years ago
- ☆18Nov 11, 2024Updated last year
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆389Apr 22, 2025Updated last year
- ☆15Apr 11, 2024Updated 2 years ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆226Feb 13, 2025Updated 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.
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆79Jun 14, 2024Updated last year
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆35Jun 12, 2024Updated last year
- AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference☆20Jan 24, 2025Updated last year
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,206Apr 18, 2026Updated 2 weeks ago
- ☆59May 19, 2025Updated 11 months ago
- [ACL Findings 2026] Official Implementation of "FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acc…☆31Apr 14, 2026Updated 3 weeks ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆160Dec 23, 2025Updated 4 months ago
- ☆11Feb 5, 2026Updated 3 months ago
- [ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆82Jul 14, 2025Updated 9 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.
- PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation☆32Nov 16, 2024Updated last year
- ☆17May 10, 2024Updated last year
- ☆85Apr 18, 2025Updated last year
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆28Apr 15, 2025Updated last year
- ☆10Feb 1, 2022Updated 4 years ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆218Mar 5, 2026Updated last month
- ☆355Apr 2, 2024Updated 2 years ago
- [ICML 2025] From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories and Applications☆52Oct 30, 2025Updated 6 months ago
- ☆14Jun 4, 2024Updated last year
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆29Mar 24, 2025Updated last year
- ☆16Jul 23, 2024Updated last year
- LongAttn ：Selecting Long-context Training Data via Token-level Attention☆15Jul 16, 2025Updated 9 months ago
- ☆66Dec 3, 2024Updated last year
- [ACL 2025] An official pytorch implement of the paper: Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement☆39May 28, 2025Updated 11 months ago
- Multi-Candidate Speculative Decoding☆40Apr 22, 2024Updated 2 years ago
- [EMNLP 2024] Tree of Problems: Improving structured problem solving with compositionality☆19Mar 4, 2025Updated last year
- Code release for VTW (AAAI 2025 Oral)☆67Nov 4, 2025Updated 6 months ago
- This repository is the official implementation of "Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE" [ACL 2026 Mai…☆38Oct 5, 2025Updated 6 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- some mixture of experts architecture implementations☆27Mar 22, 2024Updated 2 years ago
- ☆25Mar 15, 2023Updated 3 years ago
- ☆23Mar 7, 2025Updated last year
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆368Apr 13, 2026Updated 3 weeks ago
- Fast inference from large lauguage models via speculative decoding☆914Aug 22, 2024Updated last year
- [ICML 2025] MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design☆28Jul 4, 2025Updated 10 months ago
- scalable and robust tree-based speculative decoding algorithm☆377Jan 28, 2025Updated last year