Zanette-Labs / SpeculativeRejectionLinks
[NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection
β51Updated 9 months ago
Alternatives and similar repositories for SpeculativeRejection
Users that are interested in SpeculativeRejection are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Accelerationβ52Updated 6 months ago
- [NeurIPS'24] Official code for *π―DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*β112Updated 8 months ago
- β117Updated 2 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.β48Updated 10 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verificationβ62Updated last month
- Long Context Extension and Generalization in LLMsβ58Updated 11 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)β109Updated 5 months ago
- β27Updated 6 months ago
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"β95Updated 3 weeks ago
- β18Updated 8 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automatonβ31Updated 6 months ago
- β45Updated 8 months ago
- β20Updated 4 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"β219Updated 5 months ago
- LongProc: Benchmarking Long-Context Language Models on Long Procedural Generationβ26Updated 2 months ago
- β39Updated 4 months ago
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"β75Updated 3 months ago
- The official repository of the Omni-MATH benchmark.β87Updated 8 months ago
- β85Updated 7 months ago
- LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Modelsβ76Updated 10 months ago
- [ACL 2024] Long-Context Language Modeling with Parallel Encodingsβ157Updated last year
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoningβ172Updated 2 weeks ago
- The official implementation for Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Freeβ46Updated 3 months ago
- [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.β64Updated 9 months ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":β38Updated last year
- Code for the preprint "Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?"β42Updated 3 weeks ago
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learningβ108Updated 3 months ago
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"β23Updated 10 months ago
- [EMNLP 2025] LightThinker: Thinking Step-by-Step Compressionβ71Updated 4 months ago
- Implementation of "Decoding-time Realignment of Language Models", ICML 2024.β19Updated last year