Models & Labs

Llama.cpp Update Fixes iGPU Device Selection

llama.cpp ReleasesMay 31, 2026high confidence

Why it matters

→Fixes a critical bug affecting systems with integrated GPUs as main compute devices.
→Ensures proper tensor allocation and model loading on diverse hardware configurations.
→Enhances the reliability and usability of llama.cpp for developers using integrated GPUs.

Llama.cpp has released an update to fix a bug in its device selection logic that affected systems with integrated GPUs. The issue arose when RPC servers were present, causing the local iGPU to be ignored and leading to model loading failures. The update now ensures that iGPUs are included unless no GPUs are available, resolving the problem for systems where the iGPU is the main compute device. This change improves the functionality of llama.cpp on systems with integrated GPUs, such as those with large unified memory.

Read original

The story around this

Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.

llama.cpp b9243 Release Expands Platform Support

2 developments

May 20 · llama.cpp Releases
llama.cpp b9243 Release Expands Platform Support
May 31 · llama.cpp Releases
Llama.cpp Update Fixes iGPU Device Selection (This article)↳ Llama.cpp fixes a bug where RPC servers caused local iGPUs to be ignored, enabling proper model loading on systems like Strix Halo.

More from llama.cpp Releases

Coding Toolscoding

llama.cpp b12022 adds ROCm 10 and Snapdragon support

This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.

llama.cpp ReleasesNov 1, 2026

Coding Toolscoding

llama.cpp b12023 fixes shared prefix bug

This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.

llama.cpp ReleasesNov 1, 2026

Coding Toolscoding

llama.cpp b12024 adds Snapdragon and ROCm 10

This release quietly expands llama.cpp's hardware support to include Qualcomm Snapdragon devices with CPU, Adreno GPU, and Hexagon NPU acceleration. It also updates ROCm to version 10.0 for both Linux and Windows, keeping AMD users in step with the latest driver stack. CUDA builds now default to 13.4 libraries alongside 12.x options, reflecting the industry's gradual shift toward newer NVIDIA toolkits. While no new model architectures are introduced, the binary matrix grows significantly, ensuring local inference remains viable on a wider array of edge and server hardware.

llama.cpp ReleasesNov 1, 2026

More in Models & Labs

Models & Labsother

Apple Intelligence arrives in China via iOS 27.3

Apple is finally unlocking its AI suite for Chinese users with the iOS 27.3 beta, marking a significant regulatory milestone after months of approval delays. The rollout relies on Alibaba’s Qwen model rather than OpenAI, integrating features like notification summaries and visual intelligence directly into the OS. By sidestepping the new Siri in favor of established text and image tools, Apple is prioritizing immediate utility over the full generative experience. This move effectively brings Apple’s AI capabilities to a massive new market, albeit with localized constraints that distinguish it from the global release.

The Verge AIOct 30, 2026