[NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting"
☆66Jun 26, 2024Updated last year
Alternatives and similar repositories for Kangaroo
Users that are interested in Kangaroo are comparing it to the libraries listed below
Sorting:
- ☆15Apr 11, 2024Updated last year
- ☆52Feb 19, 2024Updated 2 years ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆369Apr 22, 2025Updated 10 months ago
- AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference☆20Jan 24, 2025Updated last year
- ☆15Nov 11, 2024Updated last year
- Official Implementation of FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration☆29Nov 22, 2025Updated 3 months ago
- Frequently updated list of dLLM (Diffusion Large Language Models) papers, models, and other resources☆22Jan 30, 2026Updated last month
- ☆54May 19, 2025Updated 9 months ago
- Dateset Reset Policy Optimization☆31Apr 12, 2024Updated last year
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,126Jan 24, 2026Updated last month
- ☆11Feb 5, 2026Updated last month
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆35Jun 12, 2024Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆147Dec 23, 2025Updated 2 months ago
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆74Jun 14, 2024Updated last year
- ☆16Jul 23, 2024Updated last year
- [EMNLP 2024] Tree of Problems: Improving structured problem solving with compositionality☆19Mar 4, 2025Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆216Feb 13, 2025Updated last year
- ☆22Mar 7, 2025Updated 11 months ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆277Aug 31, 2024Updated last year
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆74Jul 14, 2025Updated 7 months ago
- [ACL 2025] An official pytorch implement of the paper: Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement☆39May 28, 2025Updated 9 months ago
- ☆14Jan 24, 2025Updated last year
- Accelerating LLM inference with techniques like speculative decoding, quantization, and kernel fusion, focusing on implementing state-of-…☆11Jul 1, 2025Updated 8 months ago
- ☆15Jan 12, 2026Updated last month
- LongAttn ：Selecting Long-context Training Data via Token-level Attention☆15Jul 16, 2025Updated 7 months ago
- Learning to Skip the Middle Layers of Transformers☆17Aug 7, 2025Updated 6 months ago
- 🚀 Sliding Window Attention Training for Efficient Large Language Models☆16Dec 8, 2025Updated 2 months ago
- [ICML 2025] From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories and Applications☆52Oct 30, 2025Updated 4 months ago
- ☆28May 24, 2025Updated 9 months ago
- Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding.☆13Nov 19, 2024Updated last year
- ☆13Jan 22, 2025Updated last year
- ☆85Apr 18, 2025Updated 10 months ago
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆26Apr 15, 2025Updated 10 months ago
- ☆10Feb 1, 2022Updated 4 years ago
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆16Dec 19, 2024Updated last year
- The official repo of continuous speculative decoding☆31Mar 28, 2025Updated 11 months ago
- ☆64Dec 3, 2024Updated last year
- ☆352Apr 2, 2024Updated last year
- some mixture of experts architecture implementations☆26Mar 22, 2024Updated last year