Rank #193 · on radar since 2026-07-07
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
vllm is a tool in the AI builder stack on the Cresting radar since 2026-07-07, currently ranked #193 of 2371 tracked tools with a momentum score of 58.1. It has 85,650 GitHub stars (+72 in the last 7 days). Momentum measures how fast a tool is rising, not how big it is; the score recomputes hourly from public signals.
Momentum
58.1
24h· new7d· new
Why it's ranked
Every score decomposes into published factors — the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.976 |
| Recency boost | 0.000 |
| Signal decay | 0.991 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+33 in window · 19,093 latest · 2 snapshots
github · stars+72 in window · 85,650 latest · 2 snapshots
Related tools
- Vibe-ResearchVibe-Research: Your Personal Trading Research Agent · A股/美股/港股 的个人投研 Agent：每日复盘、资讯雷达、个股数据、板块中心、我的持仓、研究记录。Vibe-Research 把数据和功能配齐，由你自己的 AI 驱动投资研究。#2 · 479★
- openscienceThe open-source AI workbench for scientific research#3 · 1,466★
- hermexNative iPhone app for your Hermes agent#10 · 683★
- CSSwitch让 Claude Science 的推理走自选的第三方 API（DeepSeek / 通义千问 / 任意 OpenAI 兼容端点），保留工具调用·Skill·MCP·代码执行，含本地虚拟登录跳过。macOS 菜单栏 app。仅供个人学习研究，使用者自负风险。#12 · 305★
- TalosGPU worker client for the Talos network. Pairs with your Talos account, serves open-model inference jobs over a WebSocket, and reports uptime for payouts.#13 · 725★