Open source

ggml-org/llama.cpp b10970

GitHub Releases · github-actions[bot] · 3 days ago

<details open> HIP: fattn-mma: use fp32 accumulation on MFMA devices (#28576) use fp32 accumulators in fattn-mma on CDNA </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/47450174> **macOS/iOS:** - [macOS Apple…

Open on github.com ↗

Source and ranking details

Source adapter: github-releases
Source weight: 3
Points: 0
Age: 85.2 h
Stored score: 0.00066
Current score: 0.00064
First seen: 2026-09-15T08:37:06.089Z

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.