cd /news/artificial-intelligence/after-3-5-years-llama-cpp-finally-ca… · home › topics › artificial-intelligence › article
[ARTICLE · art-169286] src=runtimewire.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

After 3.5 years, llama.cpp finally calls itself 1.0

Georgi Gerganov released llama.cpp and ggml v1.0.0 on November 13th, putting the C/C++ inference libraries behind much of local AI on formal semantic versioning for the first time in the project's 3.5-year history. The release covers libllama and libggml, with breaking API and ABI changes now tied to major version numbers.

by read1 min views1 publishedNov 13, 2026
After 3.5 years, llama.cpp finally calls itself 1.0
Image: Runtimewire (auto-discovered)

Georgi Gerganov's libllama and libggml get formal semantic versioning on November 13th, with breaking API and ABI changes now tied to major releases.

        By [Ryan Merket](https://runtimewire.com/author/ryan-merket)
        · Published 
        · Updated 

Georgi Gerganov released llama.cpp and ggml v1.0.0 on November 13th, putting the C/C++ inference libraries behind much of local AI on formal semantic versioning for the first time in the project's 3.5-year history.…

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @llama.cpp 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/after-3-5-years-llam…] indexed:0 read:1min 2026-11-13 · —