llama.cpp release adds MUSA support and updates CUDA versions

The open‑source Llama.cpp library now handles MUSA GPUs and includes builds for CUDA 12.8 and 13.4.

NoteOossaPublished by Oossa: September 30, 2026 at 12:07 PM UTC1 min read

1 sources ↓Produced and translated with AI assistance. Check the original sources below.

The ggml‑org team released a new version of llama.cpp on September 30, 2026. It fixes a problem where the MUSA GPU driver did not define CUDA_ARCH, causing some kernels to compile empty. The patch adds proper architecture detection and removes redundant checks. The release also lists many pre‑built binaries, now covering CUDA 12.8 and 13.4 on Linux and Windows, plus support for various ARM and Apple Silicon targets.

Why it matters

Developers can now run Llama.cpp on MUSA GPUs and newer CUDA versions without manual patches.

Sources & references

1 sources

llama.cppSource published: Sep 30, 2026Read original source

Published by: OLY Europe LTD (VAT BG207334983), General Tsimerman 56, 9002 Varna, BGReport an error

Last updated: September 30, 2026·Markdown

Was this article useful?

llama.cpp release adds MUSA support and updates CUDA versions

Why it matters

Sources & references

Read next

Deepseek releases open‑source tools for Huawei Ascend AI chips

Oído runs speech recognition on a $5 ESP32 microcontroller

Google’s AI contribution pilot pays a handful of publishers very little