Models & Labs
b9119 release addresses Intel GPU performance
llama.cpp Releaseshigh confidence
Why it matters
- →Fixes a critical performance issue for Intel GPU users on Windows.
- →Ensures better efficiency by optimizing BF16 workload handling.
- →Reinforces llama.cpp's commitment to cross-platform performance improvements.
The latest b9119 release of llama.cpp addresses a performance regression issue on Windows for Intel GPU BF16 workloads, particularly affecting Xe2 and newer models. This update is crucial for users relying on Vulkan, as it restores expected performance levels. Additionally, the release includes a refactor to optimize the use of l_warptile, ensuring it is only used when coopamt is available for BF16. This release underscores llama.cpp's ongoing efforts to enhance performance across various hardware platforms.
Read originalThe 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.
What happened next
- 1llama.cpp b9820 Release Enhances CUDA Performance
llama.cpp Releases · June 28, 2026 · Same story
- 2Llama.cpp b9932 Release Enhances Performance
llama.cpp Releases · July 9, 2026 · Same story
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 Releases
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.
