No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Xiaohao-Liu · LLM Plugin · ★ 205
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Awesome-Multi-Token-Prediction safe to install? View the security audit →
Awesome Multi-Token Prediction (MTP!) A curated list of papers, tools, and resources on Multi-Token Prediction (MTP) and related techniques in Large Language Models (LLMs), Speech-Language Models (SLMs), and more. Multi-Token Prediction (MTP) is an emerging paradigm that enhances the efficiency and capability of language and multimodal models by allowing them to predict multiple tokens simultaneously. This repository collects recent research and implementations in this exciting direction. 🔬 Recent Papers (2026)
| Stars | 205 |
| Forks | 12 |
| Category | LLM Plugin |
| Quality Score | 58.1779373034814/100 |
| Last Updated | 2026-09-08 |
| Created | 2025-06-20 |
| Est. Tokens | ~17k |
These tools work well together with Awesome-Multi-Token-Prediction for enhanced workflows:
Looking for a Awesome-Multi-Token-Prediction alternative? If you're comparing Awesome-Multi-Token-Prediction with other llm plugin tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
irresponsible innovation. Try now at https://chat.dev/
It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learni
A curated list of awesome MCP servers focused on DevOps tools and capabilities.
📦️ A fast, secure MCP server that extends its capabilities through WebAssembly plugins.
Flow-Like: Strongly Typed Enterprise Scale Workflows. Built for scalability, speed, seamless AI integration an
MCP server for reverse engineering tasks in Ghidra 👩💻
Explore other popular llm plugin tools:
Awesome-Multi-Token-Prediction is A curated list of papers, tools, and resources on Multi-Token Prediction (MTP) and related techniques in Large Language Models (LLMs), Speech-Language Models (SLMs), and more.. It is categorized as a LLM Plugin with 205 GitHub stars.
You can find installation instructions and usage details in the Awesome-Multi-Token-Prediction GitHub repository at github.com/Xiaohao-Liu/Awesome-Multi-Token-Prediction. The project has 205 stars and 12 forks, indicating an active community.
The top alternatives to Awesome-Multi-Token-Prediction on Agent Skills Hub include LLM-VM, Awesome-LLMs-ICLR-24, awesome-devops-mcp-servers. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: