[ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.
☆56May 2, 2025Updated last year
Alternatives and similar repositories for RSD
Users that are interested in RSD are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆20May 14, 2025Updated last year
- Make reasoning models scalable☆49May 31, 2025Updated 11 months ago
- ☆34Oct 13, 2025Updated 7 months ago
- ThinK: Thinner Key Cache by Query-Driven Pruning☆29Feb 11, 2025Updated last year
- [ACL 2025] "CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought"☆17Apr 3, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆68Oct 2, 2025Updated 7 months ago
- ☆15Apr 26, 2025Updated last year
- Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination.☆22Jul 18, 2025Updated 10 months ago
- ☆20Mar 18, 2026Updated 2 months ago
- An adaptive sampling framework for Reinforce-style LLM post training.☆96Nov 29, 2025Updated 6 months ago
- ☆42Jan 16, 2026Updated 4 months ago
- Continuous Pipelined Speculative Decoding☆20Updated this week
- The official repository of NeurIPS'25 paper "Ada-R1: From Long-Cot to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization"☆24May 6, 2026Updated 3 weeks ago
- VidKV: Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models☆26Mar 26, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆83Jul 14, 2025Updated 10 months ago
- Agent-RRM: Exploring Reasoning Reward Model for Agents☆65Mar 17, 2026Updated 2 months ago
- PyTorch implementation of StableMask (ICML'24)☆15Jun 27, 2024Updated last year
- Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks☆10Oct 21, 2022Updated 3 years ago
- [EMNLP 2024] Quantize LLM to extremely low-bit, and finetune the quantized LLMs☆15Jul 18, 2024Updated last year
- PiKV: KV Cache Management System for Mixture of Experts [Efficient ML System]☆53May 19, 2026Updated last week
- JMLR Cover Letter Template☆10Dec 15, 2021Updated 4 years ago
- ☆13Nov 2, 2025Updated 6 months ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆278Aug 31, 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.
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆111Nov 22, 2025Updated 6 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆67Feb 21, 2025Updated last year
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆46Apr 21, 2024Updated 2 years ago
- RENT (Reinforcement Learning via Entropy Minimization) is an unsupervised method for training reasoning LLMs.☆43Oct 31, 2025Updated 6 months ago
- ojjson is a library designed to facilitate JSON interactions with Ollama, a large language api (LLM). It leverages the power of Zod for s…☆12Nov 7, 2024Updated last year
- [ICML 2025 Spotlight] RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding☆23Mar 2, 2025Updated last year
- Advanced Reasoning Benchmark Dataset for LLMs☆47Nov 19, 2023Updated 2 years ago
- CFG-GAN: Composite functional gradient learning of generative adversarial models☆15Jul 9, 2020Updated 5 years ago
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆268May 5, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆13Mar 28, 2025Updated last year
- ☆11Sep 25, 2025Updated 8 months ago
- Browser extension to quickly access Perplexity searchbar from any page with a shortcut☆13Oct 20, 2024Updated last year
- SMART introduces a novel test-time framework where Small Language Models (SLMs) reason step-by-step, and Large Language Models (LLMs) pro…☆12Jul 9, 2025Updated 10 months ago
- [NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis☆166Nov 6, 2025Updated 6 months ago
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆219Nov 30, 2025Updated 6 months ago
- ☆52Mar 9, 2026Updated 2 months ago