llama.cpp b9967–b9969: Adreno GPU Acceleration and OpenAI-Compatible Null Sampling
Three llama.cpp builds landed on July 12: b9968 adds OpenCL int8 dp4 dense-matmul and MoE prefill kernels for Qualcomm Adreno GPUs, improving inference throughput on Snapdragon-powered Android and Windows ARM devices; b9969 fixes a Vulkan path that routed large matmuls to the wrong tile size on Adreno, causing crashes with long prompts on quantized models; b9967 allows null values in sampling parameters so clients can explicitly request server defaults, aligning with the OpenAI sampling spec.
Why it matters
Adreno is the dominant GPU in Snapdragon SoCs powering most flagship Android phones and Copilot+ PCs, so these fixes meaningfully expand viable on-device LLM inference.
Importance: 2/5
On-device inference improvements for dominant Android/Snapdragon GPU family