Open source

ggml-org/llama.cpp b10950

GitHub Releases · github-actions[bot] · 4 days ago

<details open> ggml-cuda: fallback to F32 on device without BF16 hardware acceleration (#28846) * ggml-cuda: fallback to F32 on device without BF16 hardware acceleration: (Nvidia >= AMPERE, AMD >= RDNA3 or = CDNA) * apply logic to NVIDIA as well --------- Co-authored-by: Johanne…

Open on github.com ↗

Source and ranking details

Source adapter: github-releases
Source weight: 3
Points: 0
Age: 104.4 h
Stored score: 0.00046
Current score: 0.00045
First seen: 2026-09-14T08:37:05.845Z

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.