bk99.de entertain the web since 1997

bk99.de
HF · Local AICurated

GGML and llama.cpp join Hugging Face

Summary

GGML and llama.cpp become part of Hugging Face to develop local inference and open model formats further in the long term. The collaboration ties the Hub more closely to CPU and edge execution. GGML forms the technical basis of many quantised local models.

Ideas

  • Local AI needs open runtimes as much as available model weights.
  • Joint maintenance can reduce format and conversion breaks between the Hub and the end device.

Insights

  • Local execution only creates sovereignty with open formats and reproducible toolchains.

Facts

  • llama.cpp runs language models on CPUs and numerous other backends.

Critique

  • Bringing them together organisationally can reduce independent governance and diversity in the ecosystem.

Recommendations

  • Archive working model, quantisation and runtime versions for reproducible local setups.

References

Read the original article on Hugging Face

Search the Web Archive

HF · 2026

Security incident at Hugging Face in July 2026

Hugging Face describes a break-in in which an autonomous agent combined a prepared data source with insecure execution paths. Internal data sets and credentials were reached; according to what was known at the time, public Hub artefacts were not manipulated. The attack combined a malicious data set with remote code execution and template injection.

HF · 2026

Moving GitHub CI to Hugging Face Jobs

The guide moves compute-intensive CI steps from GitHub Actions to Hugging Face Jobs. GitHub remains the trigger and status interface, while specialised hardware runs externally. Hugging Face Jobs can run GPU and CPU tasks from GitHub workflows.

HF · 2025

Xet has arrived on the Hugging Face Hub

The Hub activates Xet as the storage layer for model and data set artefacts. Users keep Git-like workflows, while transfer and deduplication happen at block level. Xet is gradually replacing Git LFS as the storage path for large Hub files.