JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Causal Parallel Tree Drafting
☆240Oct 19, 2026Updated this week
Alternatives and similar repositories for JetSpec
Users that are interested in JetSpec are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [EMNLP2026 Main] Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆140Jul 25, 2026Updated 2 months ago
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆69Oct 31, 2025Updated 11 months ago
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆106Apr 7, 2026Updated 6 months ago
- [ICML 2026] d3LLM: Ultra-Fast Diffusion LLM 🚀☆157May 1, 2026Updated 5 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,233Updated this week
- 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.
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,243Jul 9, 2026Updated 3 months ago
- ☆397Apr 16, 2026Updated 6 months ago
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,190Aug 18, 2026Updated 2 months ago
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆234May 31, 2025Updated last year
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆121Dec 2, 2025Updated 10 months ago
- Multi-Turn RL Training System with AgentTrainer for Language Model Game Reinforcement Learning☆67Dec 18, 2025Updated 10 months ago
- [ICML 2026] Jacobi Forcing: Fast and Accurate Diffusion-style Decoding☆118Feb 20, 2026Updated 8 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆183Feb 27, 2026Updated 7 months ago
- ☆16Oct 11, 2025Updated last year
- 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.
- The official repo of "Draft-OPD: On-Policy Distillation for Speculative Draft Models"☆83Sep 4, 2026Updated last month
- Single-launch batch-1 decode engine for PrismML Bonsai 27B (ternary and 1-bit) on NVIDIA GPUs. 1.76x the vendor llama.cpp fork on H100, s…☆18Jul 16, 2026Updated 3 months ago
- Scale digital agent rollouts without pain.☆37Jun 18, 2026Updated 4 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆54May 12, 2026Updated 5 months ago
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆916Updated this week
- Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average…☆316Sep 12, 2026Updated last month
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆135Jun 24, 2025Updated last year
- ☆139May 29, 2025Updated last year
- Code for the paper ReplaySSM: Cache SSM Inputs, Not State☆57Oct 13, 2026Updated last week
- 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.
- ☆52Jul 27, 2026Updated 2 months ago
- Sparse Decoupled Attention for Efficient Long-Context LLM Inference☆74Jun 4, 2026Updated 4 months ago
- ☆37Aug 7, 2025Updated last year
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆490Sep 23, 2026Updated last month
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆173Dec 23, 2025Updated 10 months ago
- FlashMemory DS-V4 Retriever: a lightweight retriever that sparsifies DeepSeek-V4 CSA KV-cache. Weights available on Hugging Face.☆112Jul 18, 2026Updated 3 months ago
- ☆20Dec 24, 2024Updated last year
- high-performance linear attention kernel library built on TileLang☆735Oct 14, 2026Updated last week
- NVFP4 Flash-Attention 4 on BlackWell☆69Sep 26, 2026Updated 3 weeks ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,560Feb 20, 2026Updated 8 months ago
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆313Dec 1, 2025Updated 10 months ago
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,286Sep 1, 2026Updated last month
- Vortex: Programmable Sparse Attention for Agents as Algorithm Designers☆69Aug 22, 2026Updated 2 months ago
- ☆54May 19, 2025Updated last year
- [ICML 2026] When Drafts Evolve: Speculative Decoding Meets Online Learning☆127Jul 27, 2026Updated 2 months ago
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆19Mar 15, 2024Updated 2 years ago