Official implementation of "Learning To Draft: Adaptive Speculative Decoding with Reinforcement Learning" (ICLR 2026)
☆24Mar 1, 2026Updated 7 months ago
Alternatives and similar repositories for Learning-to-Draft
Users that are interested in Learning-to-Draft are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆18May 16, 2026Updated 5 months ago
- official code for GliDe with a CaPE☆21Aug 13, 2024Updated 2 years ago
- [ICML 2026] Set Diffusion: Interpolating Token Orderings between Autoregression and Diffusion for Fast and Flexible Decoding☆27Aug 9, 2026Updated 2 months ago
- [EMNLP2026 Main] Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆139Jul 25, 2026Updated 3 months ago
- Code for the paper *Attention Drift: What Speculative Decoding Models Learn*.☆33May 12, 2026Updated 5 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆56Mar 14, 2025Updated last year
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆56Jul 15, 2025Updated last year
- WIKIGENBENCH: Exploring Full-length Wikipedia Generation under Real-World Scenario (COLING 2025)☆13Jan 5, 2025Updated last year
- The fastest off-the-shelf inference algorithm for LLMs (ICLR’25)☆14Mar 8, 2025Updated last year
- ☆14Aug 2, 2026Updated 2 months ago
- MemOCR: an OCR-driven visual memory agent.☆35May 17, 2026Updated 5 months ago
- The official repo of "Draft-OPD: On-Policy Distillation for Speculative Draft Models"☆83Sep 4, 2026Updated last month
- [ICML 2025] AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism☆20Jul 14, 2025Updated last year
- Official Implementation of DART (DART: Low-Latency Parallel Drafting with Continuity-Aware Tree Pruning for Speculative Decoding, EMNLP26…☆72Aug 25, 2026Updated 2 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.
- Website for the EPFL course PHYS-642: Statistical Physics for Optimization and Learning☆11Sep 27, 2023Updated 3 years ago
- Effective CNN based capacitance models for parasitic extraction (ICCAD'21, TODAES 2023)☆13Apr 9, 2026Updated 6 months ago
- A selective knowledge distillation algorithm for efficient speculative decoders☆39Nov 27, 2025Updated 10 months ago
- Official implementation for [ICML 2026] Scalable GANs with Transformers☆23Jul 1, 2026Updated 3 months ago
- 🔥 [ICML'26] ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs☆37Aug 14, 2026Updated 2 months ago
- Source code of the paper "OpSparse: a Highly Optimized Framework for Sparse General Matrix Multiplication on GPUs"☆16Aug 23, 2022Updated 4 years ago
- ChatGPT Team 邀请自动化系统 - Cloudflare Workers 部署☆17Dec 21, 2025Updated 10 months ago
- Development repository for the Digital Terraria Lab implementation of the Sugarscape agent-based societal simulation.☆21Oct 10, 2026Updated 2 weeks ago
- [ICLR 2026] CityLens: Evaluating Large Vision-Language Models for Urban Socioeconomic Sensing☆17Jan 31, 2026Updated 8 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- [ICML 2026 Spotlight] UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models☆30Sep 9, 2026Updated last month
- Code for "Multi-level Relevance Document Identifier Learning for Generative Retrieval". ACL 2025.☆24Nov 5, 2025Updated 11 months ago
- GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts☆19Apr 24, 2026Updated 6 months ago
- [ICML 2026] NITP: Next Implicit Token Prediction for LLM Pre-training☆35May 26, 2026Updated 5 months ago
- ☆25Apr 8, 2026Updated 6 months ago
- Latent On-Policy Self-Distillation☆62Sep 22, 2026Updated last month
- ☆16Jul 1, 2026Updated 3 months ago
- Hierarchical Speculative Decoding is the SOTA verification algorithm for lossless accelerated LLM inference.☆25Apr 14, 2026Updated 6 months ago
- ☆81Apr 30, 2026Updated 5 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.
- Accurate and fast KV cache compression with a gating mechanism☆33Jul 27, 2026Updated 2 months ago
- T5 model optimized with FlexAttention☆14Sep 30, 2024Updated 2 years ago
- Official Implementation of "GRIFFIN: Effective Token Alignment for Faster Speculative Decoding"[NeurIPS 2025]☆21May 12, 2025Updated last year
- [ICML 2025 Spotlight] RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding☆23Mar 2, 2025Updated last year
- Official codebase for the paper "Sharpening Tax in Post-Training"☆31Oct 2, 2026Updated 3 weeks ago
- A sparse-first inference engine (SparseEngine).☆103Updated this week
- The first continuous diffusion language model that rivals discrete counterparts on standard language modeling benchmarks like LM1B and Op…☆96Jun 14, 2026Updated 4 months ago