File _patchinfo of Package patchinfo.18958

<patchinfo incident="18958">
  <packager>smithfarm</packager>
  <rating>moderate</rating>
  <category>recommended</category>
  <summary>Recommended update for ollama</summary>
  <description>This update for ollama fixes the following issues:

Update to version 0.9.0:

  * Ollama now has the ability to enable or disable thinking.
    This gives users the flexibility to choose the model&#8217;s thinking
    behavior for different applications and use cases.

Update to version 0.8.0:

  * Ollama will now stream responses with tool calls
  * Logs will now include better memory estimate debug information
    when running models in Ollama's engine.

Update to version 0.7.1:

  * Improved model memory management to allocate sufficient memory
    to prevent crashes when running multimodal models in certain
    situations
  * Enhanced memory estimation for models to prevent unintended
    memory offloading
  * ollama show will now show ... when data is truncated
  * Fixed crash that would occur with qwen2.5vl
  * Fixed crash on Nvidia's CUDA for llama3.2-vision
  * Support for Alibaba's Qwen 3 and Qwen 2 architectures in
    Ollama's new multimodal engine
</description>
</patchinfo>