time-to-first-token is an open-source LLM inference tool published on GitHub by patchy631. With 994 stars on GitHub, it was last updated in August 2026. Related topics: learning-resources, llm and llm-inference.
“A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.”
— patchy631, project description on GitHub
Details
| Category | Local LLMs & Inference |
|---|---|
| GitHub stars | 994 |
| Forks | 120 |
| Language | HTML |
| License | Apache-2.0 |
| Last updated | |
| Owner | patchy631 |
| Repository | patchy631/time-to-first-token |
Tags
learning-resourcesllmllm-inferencemlopsroadmapsglangvllm
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.