Open source

ggml-org/llama.cpp b10901

GitHub Releases · github-actions[bot] · 7 days ago

<details open> vulkan: use CPU writes in ggml_backend_vk_cpy_tensor_async if the context is idle (#28618) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/46709648> **macOS/iOS:** - [macOS Apple Silicon (arm64)…

Open on github.com ↗

Source and ranking details

Source adapter: github-releases
Source weight: 3
Points: 0
Age: 179.4 h
Stored score: 0.00017
Current score: 0.00017
First seen: 2026-09-11T08:37:05.875Z

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.