AI News Update

Daily digest for 2026-11-16 · 9 new stories (previously covered stories are never reposted)

Hugging Face Trending3

higurashi-ai/Haru-4B
Hugging Face Trending
unsloth/Qwen3.8-27B-GGUF
Hugging Face Trending
Edge0/Edge0-145B-NVFP4
Hugging Face Trending

Simon Willison3

datasette-maplibre 0.1a0
Simon Willison · 2026-11-15
Release: datasette-maplibre 0.1a0 The first new Datasette geospatial plugin in quite a while! This one combines the excellent MapLibre GL library with OpenFreeMap , the free vector map server operated by Zsolt Ero (you should sponsor Zsolt on GitHub .) I built most of this with a
datasette 1.0a43
Simon Willison · 2026-11-15
Release: datasette 1.0a43 I've been leaning hard into Claude Fable 5.2 to help knock things off the 1.0 milestone , which is now 53% complete. The biggest 1.0 item in this release is streaming support for output renderers - the built-in TSV and CSV export mechanisms now use this
datasette 0.65.6
Simon Willison · 2026-11-15
Release: datasette 0.65.6 I backported a minor security fix from 1.0a43: Fixed a security issue where a database registered using add_database(db, name=..., route=...) with a route that differs from its name could be downloaded from /<route>.db by actors who were denied access to

llama.cpp Releases3

b12441: webgpu: support per-head flash attention masks (#32394)
llama.cpp Releases · 2026-11-16
The flash attention shaders indexed the mask without its head dimension, so masks with ne[2] > 1 gave wrong results. The mask offset and the vec block states now include the head, broadcast as head % mask->ne[2] like the other backends. The params buffer grows to 256 bytes to fit
b12429: convert: fix ripple dflash2 NoPE metadata (#32363)
llama.cpp Releases · 2026-11-15
convert: fix ripple dflash2 NoPE metadata was wrong https://huggingface.co/ricursiveAI/Ripple-65B-Preview-DFlash2/blob/743c4669f7daa11d3ca350b9a057c059481b1afd/config.json#L45-L47 Update conversion/base.py Co-authored-by: Sigbjørn Skjæret [email protected] Co-autho
b12438
llama.cpp Releases · 2026-11-16
jinja: support json sort_keys=true ( #32366 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/68117741 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux