ollama/ollama: v0.30.5-rc0: llama.cpp version update (#16511)
English summary
This release updates ollama to v0.30.5-rc0, bumping the underlying llama.cpp version to b9509. The key change is a fix for the Gemma 4 12B multimodal projector that caused a divide-by-zero crash on x86, CUDA, Linux, and Windows systems. This update resolves several reported issues (e.g., #16479, #16489). Users running Gemma 4 models should upgrade to avoid this crash.
Chinese summary
此版本将ollama更新至v0.30.5-rc0，将底层llama.cpp版本提升至b9509。主要修复了Gemma 4 12B多模态投影仪的除以零崩溃问题，该问题在x86、CUDA、Linux和Windows系统上出现。此次更新解决了多个已报告的问题（如#16479、#16489）。运行Gemma 4模型的用户应升级以避免此崩溃。
Key points
Updated llama.cpp to b9509
将llama.cpp更新至b9509
Fixed Gemma 4 12B multimodal projector divide-by-zero crash
修复了Gemma 4 12B多模态投影仪的除以零崩溃
Resolves multiple issues (#16479, #16489, #16491, #16492, #16495)
解决了多个问题（#16479, #16489, #16491, #16492, #16495）