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.
More from coding & agent
- WebArena-Pro: a 300-task multimodal benchmark across 20 self-hosted apps for web agents — McGill-NLP · 2026-11-16
- Continual-ARC: lifelong ARC-AGI stream finds agent harness persistence rarely beats simple caching — unifyai · 2026-11-16
- Filmworkbench v0.1.2: one-prompt semi-automated short films with Claude and ComfyUI — Eastern-Ad9515 · 2026-11-16
- Stop prompting LLMs for JSON: PowerShell module Jev routes with decision models — dfinke · 2026-11-16
- I killed my 30-minute weekly sync with a decision log my agents read before every run — Humaux · 2026-11-16
- A video editor tested free MCP-connected AI editing tools: invideo, ChatCut, FableCut — lol_you_again · 2026-11-16