Open source

ggml-org/llama.cpp b10539

GitHub Releases · github-actions[bot] · 28 days ago

<details open> vulkan: FA MMQ should use fp32 for Q quantization calculations (#27413) Codex found that qd could be a denorm and 1/qd would overflow. </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/42034841> *…

Open on github.com ↗

Source and ranking details

Source adapter: github-releases
Source weight: 3
Points: 0
Age: 679.9 h
Stored score: 0.00002
Current score: 0.00002
First seen: 2026-08-21T09:03:47.926Z

Newsletter

Get practical AI engineering notes

Receive source-checked analysis of models, agents, evaluation, retrieval, and production reliability. Sent only when there is useful work to share.