Zanette-Labs / SpeculativeRejectionLinks
[NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection
β51Updated 11 months ago
Alternatives and similar repositories for SpeculativeRejection
Users that are interested in SpeculativeRejection are comparing it to the libraries listed below
Sorting:
- [NeurIPS'24] Official code for *π―DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*β114Updated 9 months ago
- Long Context Extension and Generalization in LLMsβ60Updated last year
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":β38Updated last year
- The official repository of the Omni-MATH benchmark.β88Updated 9 months ago
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"β100Updated 2 months ago
- LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Modelsβ76Updated 11 months ago
- β119Updated 3 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.β49Updated 11 months ago
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learningβ111Updated 4 months ago
- [ACL 2024] Long-Context Language Modeling with Parallel Encodingsβ163Updated last year
- β47Updated last month
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verificationβ64Updated 2 months ago
- The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sinkβ¦β81Updated 2 weeks ago
- LongProc: Benchmarking Long-Context Language Models on Long Procedural Generationβ27Updated 3 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"β228Updated 2 weeks ago
- Implementation of "Decoding-time Realignment of Language Models", ICML 2024.β19Updated last year
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Accelerationβ55Updated 7 months ago
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"β75Updated 4 months ago
- "Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding" Zhenyu Zhang, Runjin Chen, Shiwβ¦β30Updated last year
- Code for the preprint "Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?"β46Updated 2 months ago
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning" [TMLR2025]β108Updated 7 months ago
- β45Updated 10 months ago
- [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.β68Updated 11 months ago
- β86Updated 8 months ago
- β18Updated 10 months ago
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correctionβ82Updated 6 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)β110Updated 6 months ago
- [EMNLP 2025] LightThinker: Thinking Step-by-Step Compressionβ104Updated 5 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.β83Updated 3 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)β63Updated last year