The open‑source LLM runner updates its OpenCL code to correct tensor handling on Adreno GPUs and ships new binaries for macOS, iOS and Linux.
NoteOossa1 min read
The ggml‑org team released llama.cpp version b11268. The update fixes a bug in the OpenCL driver that handled tensors for the q5_K Adreno GPU kernel. New pre‑built binaries are provided for macOS Apple Silicon, Intel Macs, iOS, and several Linux configurations including CPU, Vulkan and CUDA 12.8.
The fix improves performance and stability for developers running LLMs on Android devices with Adreno GPUs.
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 b11268 ↗ | llama.cpp | Sep 30, 2026 | <details open> opencl: fix get_tensor for q5_K adreno gemm_nonshuffle kernel (#29555) </details> **Website:** - <https://llama.app> **Attest |
1 sources
