AI News Update

Daily digest for 2026-10-16 · 4 new stories (previously covered stories are never reposted)

Hugging Face Trending1

meta-models/Muse-Spark-Open-816B-A42B
Hugging Face Trending

llama.cpp Releases3

b11696
llama.cpp Releases · 2026-10-16
hexagon: correct HMX FA sinks ( #30581 ) hexagon: correct HMX FA sinks hex-fa: vectorize sinks in hmx kernels Co-authored-by: Max Krasnyansky [email protected] Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/56638901 macOS/iOS: macO
b11695
llama.cpp Releases · 2026-10-16
model : MTP support for Mellum2.1 ( #30612 ) model : MTP support for Mellum model : inline rope construction in Mellum Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/56634767 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (
b11693
llama.cpp Releases · 2026-10-16
[SYCL]: fix memory errors in mul_mat, split buffer, host pool ( #29889 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/56630304 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel