[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 11 months ago
- Make reasoning models scalable☆49May 31, 2025Updated 11 months ago
- ☆34Oct 13, 2025Updated 6 months ago
- [ACL 2025] "CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought"☆18Apr 3, 2025Updated last year
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆68Oct 2, 2025Updated 7 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination.☆22Jul 18, 2025Updated 9 months ago
- ☆20Mar 18, 2026Updated last month
- High Performance FP8 GEMM Kernels for SM89 and later GPUs.☆21Jan 24, 2025Updated last year
- ☆40Jan 16, 2026Updated 3 months ago
- The official repository of NeurIPS'25 paper "Ada-R1: From Long-Cot to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization"☆23Nov 9, 2025Updated 6 months ago
- [ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆82Jul 14, 2025Updated 9 months ago
- Agent-RRM: Exploring Reasoning Reward Model for Agents☆64Mar 17, 2026Updated last month
- PyTorch implementation of StableMask (ICML'24)☆15Jun 27, 2024Updated last year
- SLiM: One-shot Quantized Sparse Plus Low-rank Approximation of LLMs (ICML 2025)☆36Nov 28, 2025Updated 5 months ago
- 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.
- 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
- 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☆279Aug 31, 2024Updated last year
- Code for "RSQ: Learning from Important Tokens Leads to Better Quantized LLMs"☆21Mar 25, 2026Updated last month
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆110Nov 22, 2025Updated 5 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆66Feb 21, 2025Updated last year
- RENT (Reinforcement Learning via Entropy Minimization) is an unsupervised method for training reasoning LLMs.☆43Oct 31, 2025Updated 6 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [ICML 2025 Spotlight] RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding☆22Mar 2, 2025Updated last year
- Advanced Reasoning Benchmark Dataset for LLMs☆47Nov 19, 2023Updated 2 years ago
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆266May 5, 2025Updated last year
- ☆13Mar 28, 2025Updated last year
- (ACL 2025 Main) Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillat…☆34Aug 23, 2025Updated 8 months ago
- KV cache compression via sparse coding☆17Oct 26, 2025Updated 6 months ago
- ☆11Sep 25, 2025Updated 7 months ago
- 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
- SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models☆17Jun 24, 2024Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [ICML 2025] Improving Planning of Agents for Long-Horizon Tasks☆33Oct 2, 2025Updated 7 months ago
- Documentation at☆14Mar 27, 2025Updated last year
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆215Nov 30, 2025Updated 5 months ago
- [NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis☆163Nov 6, 2025Updated 6 months ago
- Official implementation of Our NeurIPS 2024 Paper "Boundary Matters: A Bi-Level Active Finetuning Method"☆14Feb 11, 2025Updated last year
- ☆52Mar 9, 2026Updated 2 months ago
- ☆13May 15, 2025Updated 11 months ago