[ICLR 2026] Draft-based Approximate Inference for LLMs
☆24Mar 10, 2026Updated 8 months ago
Alternatives and similar repositories for draft-based-approx-llm
Users that are interested in draft-based-approx-llm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [EACL 2026] TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs☆10Feb 6, 2026Updated 9 months ago
- ☆20May 26, 2026Updated 5 months ago
- [WACV 2025 Oral] Counting Guidance for High Fidelity Text-to-Image Synthesis☆15Jul 4, 2025Updated last year
- [ICML 2025] Parameter-Efficient Fine-Tuning of State Space Models☆25Jun 9, 2025Updated last year
- ☆15Aug 11, 2025Updated last year
- 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.
- [NeurIPS 2026] EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts☆19Oct 22, 2026Updated 3 weeks ago
- [ECCV 2024] Official Pytorch Implementation for "Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editing"☆34Jun 16, 2025Updated last year
- ☆37Feb 11, 2025Updated last year
- [NeurIPS 2026] AsyncOPD: How Stale Can On-Policy Distillation Be?☆40Oct 28, 2026Updated 3 weeks ago
- [ICLR 2026] ParallelBench: Understanding the Tradeoffs of Parallel Decoding in Diffusion LLMs☆50Mar 27, 2026Updated 7 months ago
- Implementation and dataset for paper "Can MLLMs Perform Text-to-Image In-Context Learning?"☆48Jun 2, 2025Updated last year
- UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation☆16Aug 12, 2025Updated last year
- [NeurIPS 2025] Multipole Attention for Efficient Long Context Reasoning☆29Dec 5, 2025Updated 11 months ago
- KV Admission: Learning What to Write for Efficient Long-Context LLM Inference (EMNLP 2026 Main)☆16Oct 6, 2026Updated last month
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Code repo for "CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs".☆17Sep 15, 2024Updated 2 years ago
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆123Dec 2, 2025Updated 11 months ago
- 삼각형의 실전! Triton☆16Feb 15, 2024Updated 2 years ago
- codebase for Coruscant: Co-Designing GPU Kernel and Sparse Tensor Core to Advocate Unstructured Sparsity in Efficient LLM Inference☆11Oct 17, 2025Updated last year
- [ICLR 2026] LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation☆14Mar 16, 2026Updated 8 months ago
- [NeurIPS 2026] DAWN: Dependency-Aware Fast Inference for Diffusion LLMs.☆13Nov 7, 2026Updated last week
- ☆14Mar 14, 2023Updated 3 years ago
- Official Implementation for [ICLR26] DefensiveKV: Taming the Fragility of KV Cache Eviction in LLM Inference☆62Mar 28, 2026Updated 7 months ago
- The official implementation of the paper "A Dual-Space Framework for General Knowledge Distillation of Large Language Models".☆17Jan 4, 2026Updated 10 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆14Dec 12, 2024Updated last year
- [ICML 2025] LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models☆16Nov 4, 2025Updated last year
- [ICML 2026] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning☆36Sep 12, 2025Updated last year
- ☆11Aug 21, 2023Updated 3 years ago
- ☆14Sep 7, 2024Updated 2 years ago
- Code for "The Expressive Power of Low-Rank Adaptation".☆21Apr 19, 2024Updated 2 years ago
- [MLSys 2026] Official code of SkipKV: Selectively Skip KV Generation and Storage for Efficient Inference with Large Reasoning Models.☆16Oct 26, 2026Updated 3 weeks ago
- Code for reproducing experiments performed for Accoridon☆13Jun 11, 2021Updated 5 years ago
- ☆10Mar 1, 2024Updated 2 years 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.
- ☆16Apr 10, 2023Updated 3 years ago
- [ICML 2025 Spotlight] RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding☆23Mar 2, 2025Updated last year
- Official implementation of Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs (ICLR 2024).☆45Aug 6, 2024Updated 2 years ago
- ☆17Jun 25, 2024Updated 2 years ago
- [EMNLP 2025] KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts☆11Sep 5, 2025Updated last year
- FR-Train: A Mutual Information-Based Approach to Fair and Robust Training (ICML 2020)☆13Jun 3, 2021Updated 5 years ago
- ☆339Jul 10, 2025Updated last year
Are these results useful?