This repository is the official implementation of "Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE" [ACL 2026 Main Accepted]
☆39Oct 5, 2025Updated last year
Alternatives and similar repositories for Jakiro
Users that are interested in Jakiro are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆56Mar 14, 2025Updated last year
- [ICML 2025] AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism☆20Jul 14, 2025Updated last year
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,304Jun 27, 2026Updated 4 months ago
- ☆19Sep 10, 2026Updated last month
- ☆15May 27, 2025Updated last year
- 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.
- ☆13Oct 6, 2024Updated 2 years ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆414Apr 22, 2025Updated last year
- Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''☆32Oct 24, 2024Updated 2 years ago
- Visualize the Expert Parallelism Load Balancer☆18Mar 15, 2025Updated last year
- PTXBench: an open-source environment to evaluate GPU kernel languages for LLM agents☆38Updated this week
- persistent kernel sample implementation of iterative stencil solver and conjugate gradient solver☆14May 24, 2023Updated 3 years ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,571Feb 20, 2026Updated 8 months ago
- ☆10Jan 27, 2026Updated 9 months ago
- Anatomy of High-Performance GEMM with Online Fault Tolerance on GPUs☆14Apr 3, 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.
- Accepted by NAACL 2025 main conference.☆11Jan 24, 2025Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆173Dec 23, 2025Updated 10 months ago
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆98Aug 20, 2023Updated 3 years ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆230Feb 13, 2025Updated last year
- ☆16Apr 17, 2026Updated 6 months ago
- Fast inference from large lauguage models via speculative decoding☆927Aug 22, 2024Updated 2 years ago
- The fastest off-the-shelf inference algorithm for LLMs (ICLR’25)☆14Mar 8, 2025Updated last year
- (ICML 2025) Rethinking Chain-of-Thought from the Perspective of Self-Training☆13Feb 15, 2025Updated last year
- Continuous Pipelined Speculative Decoding☆22May 25, 2026Updated 5 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.
- GCAPS: GPU Context-Aware Preemptive Scheduling Approach☆19Mar 22, 2026Updated 7 months ago
- ☆25Jun 10, 2025Updated last year
- ☆20Jun 17, 2024Updated 2 years ago
- Imagined Speech Classification with Kara One Database☆11Jun 2, 2021Updated 5 years ago
- ModSleuth builds evidence-grounded dependency graphs for LLM releases from public artifacts such as model cards, dataset cards, technical…☆17Jun 15, 2026Updated 4 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,265Updated this week
- [EMNLP2026 Main] Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆141Jul 25, 2026Updated 3 months ago
- Adapt full attention LLM to sliding window attention☆14Feb 20, 2026Updated 8 months ago
- Professional StagingFramework stagingframework-engine with StagingFramework-optimized scalable-architecture and enterprise enterprise-gra…☆11Aug 3, 2025Updated last year
- 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.
- A curated list of Parameter Efficient Fine-tuning papers with a TL;DR☆13Sep 19, 2024Updated 2 years ago
- vLLM wall-clock emulation pluging to allow running the real vllm serve and benchmark without gpu with simple mocking☆16Aug 21, 2026Updated 2 months ago
- A module for the Insight Toolkit (ITK) that provides a generic, modular, and extensible architecture for lesion sizing algorithms in medi…☆10Oct 13, 2026Updated 3 weeks ago
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆35Jun 12, 2024Updated 2 years ago
- ☆10Dec 7, 2024Updated last year
- 此存储库展示了用于检索增强生成（RAG）系统的各种先进技术。RAG 系统将信息检索与生成模型相结合，以提供准确且上下文丰富的响应。☆10Sep 24, 2024Updated 2 years ago
- A Codex skill for evidence-grounded paper reading, reusable academic writing, literature synthesis, and research co-creation. 论文深读、写作迁移与研…☆15Oct 26, 2026Updated last week