[ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.
☆58May 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
- [COLM 2026] An efficient 3D sampling method for long-CoT LLM.☆16May 25, 2025Updated last year
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆77Oct 2, 2025Updated last year
- Make reasoning models scalable☆51Jun 2, 2026Updated 5 months ago
- ThinK: Thinner Key Cache by Query-Driven Pruning☆30Jun 2, 2026Updated 5 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆14Jun 10, 2025Updated last year
- [ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆86Jul 14, 2025Updated last year
- PyTorch implementation of StableMask (ICML'24)☆15Jun 27, 2024Updated 2 years ago
- Self-Hinting Language Models Enhance Reinforcement Learning☆30Mar 28, 2026Updated 7 months ago
- ☆34Oct 13, 2025Updated last year
- CSV-Decode: Certifiable Sub-Vocabulary Decoding for Efficient Large Language Model Inference☆13Aug 1, 2026Updated 3 months ago
- ☆12Jul 25, 2025Updated last year
- [ACM MM 2025 Oral] TinyServe: Query-Aware Page Allocation Optimization☆12Oct 26, 2026Updated 2 weeks ago
- [ACL 2026 Main] Official Repo for Paper "Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Ali…☆17Jul 1, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ACL 2025] "CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought"☆17Apr 3, 2025Updated last year
- ☆20Mar 18, 2026Updated 7 months ago
- [NeurIPS 2025] Official PyTorch implementation for the paper AutoJudge: Judge Decoding Without Manual Annotation☆21Dec 22, 2025Updated 10 months ago
- A Collection for Distributed Reinforcement Learning Papers☆18Sep 24, 2025Updated last year
- Continuous Pipelined Speculative Decoding☆22May 25, 2026Updated 5 months ago
- Official PyTorch implementation for Training Unbiased Diffusion Models From Biased Dataset in ICLR 2024.☆15Apr 30, 2024Updated 2 years ago
- Open Source Projects from Pallas Lab☆21Oct 10, 2021Updated 5 years ago
- ☆15Apr 26, 2025Updated last year
- ☆18Apr 23, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Official Implementation of "GRIFFIN: Effective Token Alignment for Faster Speculative Decoding"[NeurIPS 2025]☆21May 12, 2025Updated last year
- CREST is a training-free test-time steering framework that discovers cognitive heads via simple offline calibration and then rotates acti…☆12Oct 22, 2026Updated 3 weeks ago
- This is the official repo for Towards Uncertainty-Aware Language Agent.☆31Aug 15, 2024Updated 2 years ago
- T5Patches is a set of tools for fast and targeted editing of generative language models built with T5X.☆12May 31, 2024Updated 2 years ago
- 🔥 Must-read papers for LLM-based Latent Reasoning☆10Mar 7, 2025Updated last year
- ☆68May 19, 2025Updated last year
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆231Nov 30, 2025Updated 11 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆70Feb 21, 2025Updated last year
- [NeurIPS'25] The official code of "PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning"☆30Mar 30, 2026Updated 7 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- High Performance FP8 GEMM Kernels for SM89 and later GPUs.☆21Jan 24, 2025Updated last year
- ☆274May 14, 2025Updated last year
- VidKV: Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models☆25Mar 26, 2025Updated last year
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…☆44Sep 22, 2024Updated 2 years ago
- Convert your language model into a byte-level one!☆14Feb 26, 2026Updated 8 months ago
- The official implementation for "Mitigating Overthinking in Large Reasoning Models via Manifold Steering"☆16May 29, 2025Updated last year
- Implementation of "RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm"☆18Apr 11, 2025Updated last year
Are these results useful?