The open‑source LLM runtime now can be compiled with IBM's ZDNN library, though tests are not included yet.
NoteOossa1 min read
The llama.cpp project added a build option for the ZDNN backend, a library that speeds up matrix math on IBM Z hardware. The change was committed by Aaron Teo on Sep 30 2026. The new code compiles the backend but does not run any tests yet.
It lets developers try llama.cpp on IBM Z systems, potentially improving performance for large‑language‑model inference.
Models
OpenAI’s new GPT‑6.1 Sol keeps the $2‑$10 per‑million‑token rate while claiming stronger performance, undercutting Anthropic’s Claude and DeepSeek models.
Models
The new v4 and v4 Turbo voices cost $0.08 and $0.04 per 1,000 characters, with a promotional cut to $0.022 and $0.011 per 1,000 until Oct 12.
Models
Oracle’s new Fusion Claw runtime lets its Fusion apps handle multi‑step jobs like staffing and accounting, using AI for reasoning while keeping calculations outside the model.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
| # | Source | Outlet | Date | Key takeaway |
|---|---|---|---|---|
| 1 | ggml-org/llama.cpp b11269 ↗ | llama.cpp | Sep 30, 2026 | <details open> ci: add zdnn backend build but not test (#29541) * ci: add zdnn backend build but not test Signed-off-by: Aaron Teo <aaron.te |
1 sources
