time-to-first-token

A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.

patchy631/time-to-first-token

View on GitHub ↗

A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.

time-to-first-token grew +4.6% in the last 30 days, ranks 7th of 26 in Roadmaps, last commit 69 days ago.

Star trajectory

79 days tracked
2026-08-051k stars today2026-10-23
Momentum

+4.6% in 30d, above the Roadmaps median of +2.9%.

Maintenance

Last commit 69 days ago, staler than the median of 44d.

How it compares in Roadmaps

time-to-first-token
1k
stars
+4.6% 30d
commit 69 days ago
Roadmaps median
690.5
stars
+2.9% 30d
commit ~44d ago
Leader · cs249r_book
29.1k
stars
+2.5% 30d
commit today

Ranked 7th of 26 by stars.

Language
HTML
License
Apache License 2.0
Contributors
1
Forks
111
Watchers
6
Open issues
0
Releases
0
Created
2026-08-02
Stars this week
+24

You've seen where time-to-first-token stands today.

Get the moves before everyone else: the 5 Roadmaps repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain time-to-first-token?

Claim this page to add your own call-to-action.

Claim this page