AI tool
time-to-first-token
A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.
- Rank
- #12 of 2,811
- Stars
- 289★ +9/wk
- On radar
- since 2026-08-04
Momentum
rate of rise, not size · recomputes hourly
77.3
24h· new7d· new
Collecting daily history; the trend chart appears after 3 days on the radar
Why it's ranked
time-to-first-token is a tool in the AI builder stack ranked #12 of 2,811 on the Cresting momentum radar, with a score of 77.3. It has 289 GitHub stars, +9 in the last 7 days, and has been tracked since 2026-08-04.
Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.829 |
| Recency boost | 0.835 |
| Signal decay | 0.998 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+0 in window · 23 latest · 2 snapshots
github · stars+9 in window · 289 latest · 2 snapshots
Related tools
- kimi-k3-in-cA 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.#1 · 2,002★
- DeterminFlowA production-oriented AI workflow runtime for building, validating, recovering, and shipping complex AI workflows as dependable services. 面向生产的 AI 工作流运行时：快速开发、验证和恢复复杂 AI 工作流，并将其稳定交付为服务。#7 · 187★
- codex-vision-proxy让纯文本模型在 Codex 中无障碍调用内置看图工具（view_image）的方案，附为纯文本 LLM 设计的视觉工具包&skill ｜ Let text-only models call Codex's built-in view_image seamlessly, plus a vision toolkit&skill designed for text-only LLMs.#8 · 273★
- ratchetYour agent reads the rules. This checks whether it followed them.#13 · 430★
- pinvou-agentOpen-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.#16 · 324★