BaohaoLiao / RSDLinks
[ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.
☆46Updated 4 months ago
Alternatives and similar repositories for RSD
Users that are interested in RSD are comparing it to the libraries listed below
Sorting:
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆87Updated 6 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆49Updated last month
- ☆130Updated 2 weeks ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆53Updated 6 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆249Updated 3 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆102Updated last month
- Simple extension on vLLM to help you speed up reasoning model without training.☆184Updated 3 months ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆169Updated last month
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆93Updated 2 months ago
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs