llama.cpp offloads CI caches and runners to Hugging Face to survive 35 PRs/day

ggerganov · x · 2026-11-16

Georgi Gerganov explains how llama.cpp optimized its CI over recent months: using HF Buckets to store most GitHub Actions caches and HF Jobs to add extra CI runners, detailed in a new HF blog post. Scale context: 3,181 PRs (about 35/day) from August-October 2026, 1,802 merged, with 100+ jobs per full CI run — some 30 minutes, plus multi-hour pre-release builds. A practical playbook for large open-source CI infrastructure.

Original post →

More from coding & agent

coding & agent channel →